© 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. 10-GEMMASCOPE-RES-131K
    7. 71061
    Prev
    Next
    INDEX
    Explanations

    enjoy youruse licenseif youthe movie'sthe bodySoluble

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

    The neuron fires on text that reads like a technical specification or instruction heading, especially architectural or room‐layout requirements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     associée
    -1.73
     identifiés
    -1.48
     inférieure
    -1.48
     empê
    -1.48
     produite
    -1.47
     autorisés
    -1.46
     ซึ่ง
    -1.41
     perdiendo
    -1.41
     réduite
    -1.40
     három
    -1.38
    POSITIVE LOGITS
     this
    2.20
     your
    2.17
     their
    2.03
     it
    2.03
    机遇
    1.53
     its
    1.49
     turista
    1.46
     are
    1.43
    2
    1.41
    他也
    1.41
    Activations Density 0.022%

    No Known Activations