© 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. 15320
    Prev
    Next
    INDEX
    Explanations

    accountable by, suggests that, conclusion that

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

    scale is key

    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
    قال
    0.42
     Zukunft
    0.41
     Brook
    0.40
     قال
    0.39
     Revelation
    0.39
     گفت
    0.38
     Consid
    0.38
    谓
    0.38
     అలాగే
    0.38
     ไป
    0.38
    POSITIVE LOGITS
     শরণার্থী
    0.43
    aped
    0.42
    𝗱
    0.41
    財布
    0.40
    新
    0.39
    adjustment
    0.39
    uated
    0.38
    surface
    0.38
    重量
    0.37
    mechanism
    0.37
    Activations Density 0.000%

    No Known Activations