© 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. 84627
    Prev
    Next
    INDEX
    Explanations

    arrangements and recommendations

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

    code blocks and specific terms

    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
     be
    0.46
    เป็น
    0.44
     IntelliJ
    0.44
     fest
    0.44
     spat
    0.44
    enced
    0.43
     kwenye
    0.42
    )|$(
    0.42
     it
    0.42
     if
    0.42
    POSITIVE LOGITS
    vamo
    0.54
    circulation
    0.49
     concentración
    0.46
    जाम
    0.46
    чными
    0.46
    workouts
    0.44
    concentration
    0.44
    catering
    0.44
     অপহরণকারীদের
    0.43
    рот
    0.43
    Activations Density 0.000%

    No Known Activations