© 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. 40870
    Prev
    Next
    INDEX
    Explanations

    introducing specific entities

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

    severe damage

    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
    asmuch
    0.54
    의
    0.50
     حکمت
    0.49
     مشکلات
    0.49
     حدود
    0.48
     ಅಧ್ಯ
    0.48
     अध्याय
    0.47
     discrepancies
    0.46
     공부
    0.45
     अध्ययन
    0.45
    POSITIVE LOGITS
     Us
    0.45
     yours
    0.41
    s
    0.40
    ហា
    0.39
     motorbike
    0.39
    <0x0D>
    0.38
    salt
    0.38
    лье
    0.38
     οποίο
    0.38
     dành
    0.38
    Activations Density 0.000%

    No Known Activations