© 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. 105374
    Prev
    Next
    INDEX
    Explanations

    position in

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

    need to adhere to strict

    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
    逾
    0.49
    Q
    0.49
     inwoners
    0.48
    UMPS
    0.47
     doanh
    0.46
     ASN
    0.46
    สง
    0.46
    瀝
    0.46
    vai
    0.45
    業
    0.45
    POSITIVE LOGITS
    hausen
    0.49
    abbat
    0.48
    kowe
    0.47
     Dracula
    0.46
    hers
    0.46
     coerce
    0.45
    iguity
    0.45
     infantil
    0.44
     अवस्थ
    0.44
    ètes
    0.44
    Activations Density 0.001%

    No Known Activations