© 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. 198616
    Prev
    Next
    INDEX
    Explanations

    top of reference

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

    Chat, mobile, and research

    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
    titor
    0.53
    जलवायु
    0.52
    ")}}'
    0.52
    judul
    0.52
     உதாரணமாக
    0.51
    ޏ
    0.51
    उदाहरण
    0.50
    hidrat
    0.50
    拶
    0.49
    akkhati
    0.49
    POSITIVE LOGITS
    :
    0.54
     a
    0.49
     to
    0.47
     organs
    0.47
     generate
    0.47
     che
    0.46
     novamente
    0.46
     mobile
    0.45
     Account
    0.45
     milhões
    0.44
    Activations Density 0.000%

    No Known Activations