© 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. 34185
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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
    就會
    -1.22
    Tors
    -1.20
    Oph
    -1.11
    睜
    -1.10
    ushchev
    -1.03
    举动
    -1.03
    尷
    -1.02
    厲害
    -1.02
    帶來
    -1.00
    也将
    -0.99
    POSITIVE LOGITS
     that
    1.50
     outono
    1.30
     ability
    1.26
     adanya
    1.16
     possibility
    1.16
    ♥️
    1.13
    Ꮄ
    1.10
     』
    1.08
     a
    1.07
     fact
    1.06
    Activations Density 0.050%

    No Known Activations