© 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. 139488
    Prev
    Next
    INDEX
    Explanations

    accessible to the public

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

    affl cdfunding radiography Tang

    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
    મ
    0.55
     COMPANIES
    0.54
     EMAIL
    0.54
     компанию
    0.54
    ри
    0.53
     эту
    0.52
    та
    0.51
     poissons
    0.50
     Osama
    0.49
    つ
    0.48
    POSITIVE LOGITS
    وبه
    0.49
    dfunding
    0.46
    annis
    0.44
    tang
    0.44
    deriv
    0.44
    ographer
    0.43
    انب
    0.43
    abler
    0.43
    affiliation
    0.43
    ستگی
    0.42
    Activations Density 0.000%

    No Known Activations