© 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. 15705
    Prev
    Next
    INDEX
    Explanations

    coordinates (0,0)

    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
    に入れる
    -1.55
    すみません
    -1.53
    あー
    -1.53
    に似
    -1.48
    になったら
    -1.47
    の準備
    -1.45
     jakiś
    -1.44
    のですか
    -1.40
    𖣔
    -1.37
    来週
    -1.36
    POSITIVE LOGITS
    を
    1.91
     in
    1.59
    <bos>
    1.42
    를
    1.29
    そして
    1.29
    も
    1.27
    は
    1.25
    で
    1.22
    方針
    1.15
    a
    1.15
    Activations Density 0.008%

    No Known Activations