© 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. 183318
    Prev
    Next
    INDEX
    Explanations

    but not

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

    explaining validation

    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
     रहती
    0.55
    Docket
    0.54
     過
    0.53
    療
    0.52
    isTrack
    0.52
    RecordPtr
    0.52
    avkhat
    0.51
    顔
    0.51
     學
    0.50
    㪇
    0.50
    POSITIVE LOGITS
     brutal
    0.47
     banal
    0.46
    ’
    0.45
     ligação
    0.42
     house
    0.42
    ipy
    0.41
     stupid
    0.41
     Ust
    0.41
     league
    0.41
     ocasi
    0.40
    Activations Density 0.001%

    No Known Activations