© 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. 162487
    Prev
    Next
    INDEX
    Explanations

    search for, find

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

    don't bother with

    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
     napis
    0.43
    report
    0.43
    詃
    0.43
    interpretation
    0.42
    dried
    0.41
    गिर
    0.41
    ﹗
    0.41
    ா்
    0.41
     Toscana
    0.41
     translateY
    0.40
    POSITIVE LOGITS
    erweise
    0.59
    لاء
    0.50
    u
    0.46
    wen
    0.45
    quela
    0.45
    ela
    0.45
     صنع
    0.45
     ഭരണ
    0.43
     بعض
    0.42
    ließlich
    0.42
    Activations Density 0.002%

    No Known Activations