© 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. 124525
    Prev
    Next
    INDEX
    Explanations

    names and non-english words

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

    measurements and comparisons

    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
    Mama
    0.51
     мам
    0.50
    ôi
    0.49
     ප
    0.47
     უნდა
    0.47
    giveness
    0.46
    Semitism
    0.46
    韫
    0.46
     toată
    0.45
    Truth
    0.45
    POSITIVE LOGITS
     enqueue
    0.49
    の内
    0.46
    )}}
    0.45
     Brou
    0.44
     liberar
    0.44
    บริการ
    0.42
     Brock
    0.42
     ordering
    0.41
     Pol
    0.41
    <0xC4>
    0.40
    Activations Density 0.000%

    No Known Activations