© 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. 72466
    Prev
    Next
    INDEX
    Explanations

    opening punctuation characters

    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
    が
    -1.36
     also
    -1.36
     same
    -1.30
     now
    -1.24
    を
    -1.20
     how
    -1.14
    がありません
    -1.13
     our
    -1.09
    れません
    -1.08
     inconveniente
    -1.08
    POSITIVE LOGITS
    為に
    1.21
    方がいい
    1.16
    ところに
    1.16
     commandement
    1.13
    anmoins
    1.11
     nazi
    1.10
    ほうがいい
    1.10
    Detalles
    1.10
    Recep
    1.10
    之时
    1.09
    Activations Density 0.007%

    No Known Activations