© 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. 22-GEMMASCOPE-RES-131K
    7. 129227
    Prev
    Next
    INDEX
    Explanations

    the followed by capitalized words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Asegúrese
    -1.71
     Ofrece
    -1.63
     savag
    -1.61
     Tienes
    -1.61
    unno
    -1.56
     Aseg
    -1.55
    zzet
    -1.52
     Puedes
    -1.52
     Lleva
    -1.49
    laria
    -1.47
    POSITIVE LOGITS
     each
    1.69
     because
    1.38
     this
    1.30
     an
    1.29
     by
    1.27
     or
    1.27
     only
    1.27
    🥰
    1.25
     jaja
    1.24
     overall
    1.23
    Activations Density 0.111%

    No Known Activations