© 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. 10846
    Prev
    Next
    INDEX
    Explanations

    of followed by a number or description

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

    domain itself

    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
    軐
    0.50
    ጻ
    0.46
     आरमार
    0.46
    <unused28>
    0.44
     आकर्षण
    0.44
     привлека
    0.44
    兟
    0.44
    舩
    0.43
    ሚ
    0.43
    鎊
    0.42
    POSITIVE LOGITS
    us
    0.58
    See
    0.45
    /
    0.45
    ..
    0.43
    t
    0.42
    :
    0.42
    es
    0.42
    sim
    0.41
    ,
    0.41
    .
    0.41
    Activations Density 0.000%

    No Known Activations