© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 18961
    Prev
    Next
    INDEX
    Explanations

    actions of control

    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
    蒾
    -2.31
    鉿
    -2.20
    s
    -2.14
    踅
    -2.02
    鏵
    -1.98
    ﮯ
    -1.88
    ⦊
    -1.77
     leur
    -1.75
     THEIR
    -1.74
    ⼥
    -1.73
    POSITIVE LOGITS
     he
    2.34
    좆
    1.97
    のは
    1.88
    ка
    1.72
    gregor
    1.71
     mythological
    1.70
     terbukti
    1.65
    போ
    1.63
    に
    1.61
    ところです
    1.55
    Activations Density 0.006%

    No Known Activations