© 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. 158588
    Prev
    Next
    INDEX
    Explanations

    shut up

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

    don't skip

    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
     -
    0.60
     and
    0.55
    ,
    0.50
    l
    0.50
     cured
    0.48
     .
    0.47
    h
    0.47
    -
    0.47
     l
    0.46
     felt
    0.46
    POSITIVE LOGITS
    팥
    0.46
    इंटर
    0.46
    बह
    0.46
    풉
    0.46
    在大
    0.46
    Пет
    0.45
    གྲ
    0.45
    ėmis
    0.45
    ꯤ
    0.44
    <unused39>
    0.43
    Activations Density 0.001%

    No Known Activations