© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71640
    Prev
    Next
    INDEX
    Explanations

    academic and technical proceedings

    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
     and
    -1.80
     or
    -1.49
     our
    -1.45
    にします
    -1.36
    感じが
    -1.34
    ときは
    -1.34
    為に
    -1.32
     This
    -1.32
    ところに
    -1.27
    様な
    -1.24
    POSITIVE LOGITS
    がありますが
    1.77
    <bos>
    1.72
    最近は
    1.66
    ジナル
    1.28
    內容簡介
    1.26
     prea
    1.24
     symbole
    1.22
    genossen
    1.22
    かで
    1.20
     土豆
    1.20
    Activations Density 0.004%

    No Known Activations