© 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. 72608
    Prev
    Next
    INDEX
    Explanations

    math and measurement terms

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

    known information and conditions

    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
     alloy
    0.40
     beauty
    0.40
     島
    0.38
     angesch
    0.37
     policeman
    0.37
    кте
    0.37
     glass
    0.36
    молу
    0.36
    џ
    0.36
     естественно
    0.36
    POSITIVE LOGITS
    总
    0.43
     diketahui
    0.42
     Tue
    0.42
    Tue
    0.42
     নিশ্চিত
    0.42
     સંદ
    0.41
     totales
    0.41
    得知
    0.40
     Selasa
    0.40
     Setter
    0.40
    Activations Density 0.006%

    No Known Activations