© 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. 108934
    Prev
    Next
    INDEX
    Explanations

    rubbish disposal, everything going

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

    use following data or structures

    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
    araoh
    0.47
    orso
    0.46
    バー
    0.44
    csdn
    0.44
    ндо
    0.43
    umbled
    0.42
    ppen
    0.42
    I
    0.42
    اره
    0.42
    pielt
    0.42
    POSITIVE LOGITS
     aristocratic
    0.48
     سعید
    0.48
     suitors
    0.47
     বিলা
    0.46
     نکل
    0.45
     subcontractors
    0.45
     Sudbury
    0.44
    ...
    0.44
     meteorological
    0.43
     surfact
    0.43
    Activations Density 0.000%

    No Known Activations