© 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. 149921
    Prev
    Next
    INDEX
    Explanations

    stamped envelope, one click

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

    ASOS

    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
    ﻞ
    0.56
    f
    0.55
    c
    0.54
     chamada
    0.53
     asem
    0.51
     வால்
    0.51
    ﻢ
    0.50
    m
    0.50
     tão
    0.49
     vald
    0.49
    POSITIVE LOGITS
    ification
    0.44
    varlak
    0.42
     NIH
    0.41
    istasis
    0.41
    ctu
    0.40
    ocytosis
    0.40
    emies
    0.40
    NIH
    0.40
     हालत
    0.39
    发的
    0.39
    Activations Density 0.001%

    No Known Activations