© 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. 8180
    Prev
    Next
    INDEX
    Explanations

    space characters and punctuation

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

    .Okay

    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
     at
    0.51
    दिग्ध
    0.50
     گیا۔
    0.50
     rekan
    0.49
    গ্রহায়ণ
    0.49
    ’
    0.48
     jumpsuit
    0.48
    multiSelectList
    0.48
     사람
    0.47
    ँग्रेस
    0.47
    POSITIVE LOGITS
    ↵
    1.11
    ك
    0.90
    на
    0.82
    <0x80>
    0.80
    و
    0.79
    u
    0.78
    k
    0.77
    p
    0.76
    d
    0.70
    m
    0.70
    Activations Density 0.006%

    No Known Activations