© 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. 10-GEMMASCOPE-RES-131K
    7. 112377
    Prev
    Next
    INDEX
    Explanations

    retain the

    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
    .
    -3.98
    y
    -2.41
    >
    -2.41
    卧槽
    -2.38
    戆
    -2.36
     capace
    -2.25
    鑁
    -2.14
     教室
    -2.14
    镦
    -2.11
    蹰
    -2.05
    POSITIVE LOGITS
    潆
    2.45
    ー
    2.44
     بينما
    2.34
     тради
    2.30
    ࿚
    2.19
     dizzy
    2.19
     WHILE
    2.14
    粁
    2.14
    ―
    2.13
    >
    2.11
    Activations Density 0.008%

    No Known Activations