© 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. 139906
    Prev
    Next
    INDEX
    Explanations

    than that

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

    lists items with descriptions

    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
    Negative Logits
     mountaine
    0.49
     Mountaine
    0.49
    ္ဂ
    0.45
    ⟋
    0.44
    chens
    0.42
    SPs
    0.42
     များ
    0.42
    များသည်
    0.42
    HCM
    0.41
    verno
    0.40
    POSITIVE LOGITS
     QR
    0.47
     SHARE
    0.46
    ar
    0.44
    独
    0.44
    fé
    0.43
     Prove
    0.42
    筷
    0.42
     позволя
    0.41
     AVE
    0.41
     обеспе
    0.40
    Activations Density 0.000%

    No Known Activations