© 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. 147520
    Prev
    Next
    INDEX
    Explanations

    all safety, reimbursements, instance of

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

    supervisory management

    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
     chanson
    0.44
     veya
    0.44
    štu
    0.44
    ?
    0.43
     determinadas
    0.42
     certaine
    0.42
    torio
    0.42
    .):
    0.42
     pastor
    0.41
     recientemente
    0.41
    POSITIVE LOGITS
    чно
    0.54
    к
    0.52
    ACH
    0.50
    irai
    0.49
    ہ
    0.46
    ни
    0.46
    кої
    0.46
    స్
    0.45
    ారం
    0.45
    鰍
    0.45
    Activations Density 0.000%

    No Known Activations