© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 516
    Prev
    Next
    INDEX
    Explanations

    idioms and actions of kicking

    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
    *
    -2.31
    (
    -2.22
     With
    -2.19
     of
    -2.11
     –
    -2.00
     —
    -1.93
    “
    -1.91
    #
    -1.90
    .
    -1.85
    The
    -1.78
    POSITIVE LOGITS
     ſta
    2.14
    bbero
    2.08
    Rumah
    2.05
    鹛
    2.02
     gezond
    1.98
    archiwizowane
    1.96
    Ꮘ
    1.91
     parachoque
    1.91
    Kirche
    1.89
    靣
    1.88
    Activations Density 0.009%

    No Known Activations