© 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. 123568
    Prev
    Next
    INDEX
    Explanations

    disclose, cost, summer, enclosure

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

    modifying game or crafts

    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
    .??.??"]
    0.57
    States
    0.56
     Instances
    0.54
    ட்டிக்
    0.53
    Instances
    0.53
    圄
    0.51
    বলী
    0.50
    }[\
    0.49
    ంత్రి
    0.49
    Departments
    0.48
    POSITIVE LOGITS
    s
    0.55
    is
    0.52
     jes
    0.51
     kon
    0.47
     pediatric
    0.45
     col
    0.42
     apres
    0.42
     cores
    0.41
    ok
    0.41
    cola
    0.40
    Activations Density 0.001%

    No Known Activations