© 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. 15972
    Prev
    Next
    INDEX
    Explanations

    number of

    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
    ———
    -1.18
    ——-
    -1.02
    %%%
    -0.98
    🙁
    -0.96
     minta
    -0.96
     étions
    -0.96
     "");
    -0.93
    ➡️
    -0.92
     〜
    -0.92
    🐈
    -0.91
    POSITIVE LOGITS
    了什么
    1.12
    情节
    1.11
    有何
    1.05
    knitted
    1.05
     Phosph
    1.02
    əri
    1.02
    intéress
    1.01
     terrified
    1.00
    Dónde
    1.00
    逦
    0.99
    Activations Density 0.231%

    No Known Activations