© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113625
    Prev
    Next
    INDEX
    Explanations

    legal penalties and punishments

    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_10/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
    </strong>
    -1.47
     tdi
    -1.46
    🥳
    -1.43
     #####
    -1.42
     -----------
    -1.38
    💯
    -1.36
     fernando
    -1.34
     Both
    -1.34
    ♥️
    -1.33
     ======
    -1.32
    POSITIVE LOGITS
    “
    1.55
     a
    1.45
     生産
    1.38
    σεις
    1.31
     try
    1.30
    ヤー
    1.29
     freut
    1.29
    fford
    1.29
     leurs
    1.27
    پاسخ
    1.27
    Activations Density 0.035%

    No Known Activations