© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99905
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron is keyed to any token containing digits or hyphens (e.g. version numbers, license identifiers, or CLI switches).

    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
     angel
    -0.91
     night
    -0.74
     Angel
    -0.71
     nights
    -0.68
     triangle
    -0.67
     Default
    -0.67
    さで
    -0.67
     exist
    -0.65
     ladder
    -0.65
     Type
    -0.64
    POSITIVE LOGITS
     Takeaways
    0.70
    <0x84>
    0.70
     جوش
    0.69
    zyści
    0.69
    Modific
    0.68
    dellin
    0.68
    Mall
    0.68
    Listar
    0.66
    Française
    0.64
     Puis
    0.64
    Activations Density 0.070%

    No Known Activations