© 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. 1459
    Prev
    Next
    INDEX
    Explanations

    up/down/out/off

    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
    9
    -3.34
    .
    -3.23
    6
    -3.09
    The
    -3.06
    5
    -2.88
    3
    -2.73
    2
    -2.70
    7
    -2.64
    4
    -2.63
    8
    -2.58
    POSITIVE LOGITS
     of
    3.42
    沨
    2.58
    眥
    2.27
    СЫ
    2.19
     for
    2.11
    ⃕
    2.08
     ショット
    2.03
     also
    2.02
    РЫ
    1.97
     a
    1.95
    Activations Density 0.122%

    No Known Activations