© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92638
    Prev
    Next
    INDEX
    Explanations

    Rule or policy designation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on formal section headings and classification labels (e.g. official designations like “Site of Special Scientific Interest,” “Special Protection Area,” rule numbers, license/usage headings, stylesheet names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     émotion
    -0.81
     TGA
    -0.76
     Stomp
    -0.73
    igent
    -0.72
     narciss
    -0.72
     narcissistic
    -0.71
     Masonic
    -0.69
     Hobbes
    -0.69
    proceso
    -0.69
     TVA
    -0.68
    POSITIVE LOGITS
     policies
    2.36
     policy
    2.09
     Policies
    2.05
    policies
    1.92
    Policies
    1.80
     Policy
    1.78
    Policy
    1.72
    policy
    1.71
     POLICIES
    1.67
     POLICY
    1.59
    Activations Density 0.005%

    No Known Activations