© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13427
    Prev
    Next
    INDEX
    Explanations

    multimodal model

    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_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    forcement
    0.52
    peanut
    0.48
    protected
    0.47
    token
    0.46
    cled
    0.45
    รางวัล
    0.45
    ாச
    0.43
     carcasses
    0.43
    >);
    0.42
    nonumber
    0.42
    POSITIVE LOGITS
    ある
    0.49
    アン
    0.48
     encephalitis
    0.47
     synchron
    0.46
    asthenia
    0.44
     hypergly
    0.43
    あります
    0.43
     secretary
    0.42
     transcriptional
    0.41
     préciser
    0.41
    Activations Density 0.008%

    No Known Activations