© 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. 11200
    Prev
    Next
    INDEX
    Explanations

    power on/off states

    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
    s
    -1.66
    i
    -1.64
     RECOMEND
    -1.60
    </b>
    -1.54
     RECOMMEND
    -1.51
    he
    -1.49
    [])
    -1.47
    :“
    -1.46
    m
    -1.43
     MAKES
    -1.42
    POSITIVE LOGITS
     It
    1.78
     a
    1.65
    目錄
    1.41
     Its
    1.39
    引言
    1.38
    嗚
    1.37
     กับ
    1.34
    staa
    1.33
    There
    1.32
    sepatu
    1.32
    Activations Density 0.037%

    No Known Activations