© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48135
    Prev
    Next
    INDEX
    Explanations

    affected, inserted, modified counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CRC
    0.40
    ɬ
    0.40
     Cindy
    0.38
     dico
    0.37
     abund
    0.36
     Bez
    0.36
     '//
    0.36
     ')')
    0.36
     Premiere
    0.35
     abundance
    0.35
    POSITIVE LOGITS
    affected
    0.73
    Affected
    0.70
    Inserted
    0.68
     affected
    0.67
    inserted
    0.63
    影響
    0.60
     Affected
    0.60
     inserted
    0.59
    挿
    0.56
    影响
    0.55
    Activations Density 0.019%

    No Known Activations