© 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. 236834
    Prev
    Next
    INDEX
    Explanations

    occupations and places

    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
    u
    0.64
    retrato
    0.58
    r
    0.54
    ur
    0.53
    cí
    0.51
    ff
    0.50
    la
    0.50
    rr
    0.50
     cerrar
    0.50
    ro
    0.49
    POSITIVE LOGITS
     revolutionary
    0.50
     Elev
    0.49
    铲
    0.48
     Serv
    0.48
     Rarely
    0.48
    Villa
    0.46
    Elev
    0.46
     ധാ
    0.46
    یدہ
    0.45
     garbage
    0.44
    Activations Density 0.000%

    No Known Activations