© 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. 33141
    Prev
    Next
    INDEX
    Explanations

    boca helping hands

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

    largest, fib, abstract, infinity, mobile, greater, empty, passport, hello

    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
     Midlands
    0.40
    (,
    0.38
     Marbella
    0.38
    instag
    0.38
     Johnny
    0.38
    )([
    0.38
     Jimi
    0.38
     Marriott
    0.37
     Mahatma
    0.37
     یه
    0.37
    POSITIVE LOGITS
    _
    0.55
    CP
    0.40
    ூழ
    0.39
    Locations
    0.36
    ј
    0.36
     விரும்ப
    0.35
    ர்த
    0.35
    デビュー
    0.35
     जानकारी
    0.35
    wanie
    0.35
    Activations Density 0.011%

    No Known Activations