© 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. 64439
    Prev
    Next
    INDEX
    Explanations

    include release

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

    multilingual text descriptions

    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
    候補
    0.44
    יי
    0.44
    糖
    0.44
    占
    0.43
    emit
    0.43
    oni
    0.42
    。
    0.42
    兌
    0.42
    CHO
    0.41
    <0xF0>
    0.41
    POSITIVE LOGITS
     आंख
    0.50
    㩴
    0.48
     rythme
    0.47
    铍
    0.45
     rougeâtre
    0.44
     മിക
    0.44
    trashItem
    0.44
     આં
    0.43
     powerAll
    0.43
     Texte
    0.43
    Activations Density 0.000%

    No Known Activations