© 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. 128805
    Prev
    Next
    INDEX
    Explanations

    programming language declarations

    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
    鷽
    -1.65
     potes
    -1.63
     republi
    -1.61
    蹓
    -1.59
     indiví
    -1.59
     biela
    -1.58
     pneus
    -1.50
     plafon
    -1.49
    떳
    -1.48
     incrí
    -1.48
    POSITIVE LOGITS
    d
    1.81
    p
    1.74
    u
    1.59
    l
    1.53
     to
    1.51
     is
    1.47
    r
    1.46
     *
    1.45
    o
    1.43
     M
    1.41
    Activations Density 0.008%

    No Known Activations