© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 38665
    Prev
    Next
    INDEX
    Explanations

    keywords, hashtags, and programming terms

    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
     the
    -1.70
    際には
    -1.69
    為に
    -1.55
    えっ
    -1.45
    際に
    -1.44
    ようです
    -1.44
    ほら
    -1.43
    corrhi
    -1.43
    ためには
    -1.41
    すっ
    -1.36
    POSITIVE LOGITS
    って思
    1.40
    最近は
    1.38
    幼稚園
    1.38
    <bos>
    1.32
    作り方
    1.26
    商品は
    1.24
    礎
    1.23
    AKB
    1.18
    などが
    1.16
    でしょうね
    1.15
    Activations Density 0.016%

    No Known Activations