© 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. 77890
    Prev
    Next
    INDEX
    Explanations

    promising to

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

    concepts and specific items

    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
    aient
    0.54
    ร็จ
    0.47
    Dining
    0.45
    浆
    0.44
    Pk
    0.44
    IAM
    0.44
     بنابراین
    0.43
    虧
    0.43
    PK
    0.42
    ･･･
    0.42
    POSITIVE LOGITS
     gleichen
    0.46
     Survivors
    0.46
     stripes
    0.44
     Ext
    0.44
     crossorigin
    0.44
     Gri
    0.44
    зар
    0.44
     Kon
    0.43
     Amit
    0.42
    stripe
    0.42
    Activations Density 0.000%

    No Known Activations