© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69602
    Prev
    Next
    INDEX
    Explanations

    doors opening or closing

    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
     When
    -2.63
    geſ
    -2.25
    ⃨
    -2.17
     eine
    -2.14
    ᩠
    -2.11
    躄
    -2.02
    してました
    -2.00
     府
    -2.00
     blah
    -1.97
     を
    -1.95
    POSITIVE LOGITS
     doors
    2.66
    .
    2.27
    经理
    2.19
    ⑊
    2.16
     weitgehend
    2.16
    –
    2.16
    ra
    2.14
     impec
    2.11
     magnific
    2.08
     unfailing
    2.08
    Activations Density 0.003%

    No Known Activations