© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17699
    Prev
    Next
    INDEX
    Explanations

    the daily commute, all right

    np_acts-logits-general · gemini-2.5-flash-lite

    quest generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agan
    0.46
    omers
    0.44
    atern
    0.43
    antos
    0.42
    ligen
    0.40
    항
    0.40
    izon
    0.38
    ⿱
    0.38
    omi
    0.37
    cina
    0.37
    POSITIVE LOGITS
     مشتقه
    0.52
     மாசுபடுத்த
    0.50
     Fleurit
    0.49
    Jpeg
    0.48
     ಕಾರ್
    0.48
    stricken
    0.47
    ៦
    0.47
     সংখ
    0.47
     ngựa
    0.47
    UEFA
    0.47
    Activations Density 0.000%

    No Known Activations