© 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. 66368
    Prev
    Next
    INDEX
    Explanations

    engrave or deposit patterns

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

    custodians and sensors

    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
     Theory
    0.50
    楖
    0.48
     Canaan
    0.47
     pagan
    0.45
     tetanus
    0.44
     평
    0.44
     NRI
    0.44
     दैट
    0.43
    smt
    0.43
     sectoral
    0.43
    POSITIVE LOGITS
    ક
    0.50
    ﻟ
    0.50
    ং
    0.50
    нг
    0.48
     подписа
    0.47
     симво
    0.46
    ضای
    0.46
     бывшего
    0.46
    عيب
    0.46
     ITEMS
    0.46
    Activations Density 0.000%

    No Known Activations