© 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. 205245
    Prev
    Next
    INDEX
    Explanations

    security and technology

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

    slots and time indicators

    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
    黨
    0.51
     mexican
    0.50
     Spanien
    0.48
    etten
    0.47
     roche
    0.46
     falar
    0.45
     HOW
    0.45
     dönem
    0.44
     消費
    0.44
    egd
    0.44
    POSITIVE LOGITS
     hoops
    0.46
    𝘇
    0.44
    مک
    0.43
    ይ
    0.43
    lite
    0.42
    longitude
    0.42
    म
    0.42
    म्
    0.41
    日
    0.41
    여
    0.41
    Activations Density 0.000%

    No Known Activations