© 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. 168764
    Prev
    Next
    INDEX
    Explanations

    foreign languages and dates

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

    cost-effectiveness and copper hairs

    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
    _
    0.52
    er
    0.52
    is
    0.49
    es
    0.46
    **
    0.45
    b
    0.45
    To
    0.44
     ED
    0.44
    v
    0.44
    ed
    0.43
    POSITIVE LOGITS
     سبسڈی
    0.52
     مقدار
    0.50
     maneiras
    0.50
     vuonna
    0.50
     decembrie
    0.49
     roce
    0.49
     julho
    0.48
    fehlung
    0.48
     crebre
    0.48
     katika
    0.47
    Activations Density 0.000%

    No Known Activations