© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130468
    Prev
    Next
    INDEX
    Explanations

    glad to, return to

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

    Books, Russians, participated

    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
    s
    0.51
     abstracts
    0.48
     Oxidation
    0.46
    開業
    0.46
     Based
    0.45
    平成
    0.45
     Abstracts
    0.44
    粋
    0.44
     Opened
    0.43
    稲
    0.43
    POSITIVE LOGITS
     podstaw
    0.50
    ्याने
    0.49
    ारा
    0.48
     costruzione
    0.47
     জানিয়েছেন
    0.45
     coexist
    0.45
     früh
    0.45
     murderous
    0.44
    ack
    0.44
    ATA
    0.44
    Activations Density 0.000%

    No Known Activations