© 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. 107852
    Prev
    Next
    INDEX
    Explanations

    st act

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

    reviews, owner, hypoxia, wizard, deadlock, website, chloride, waste

    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
     Number
    0.42
     glTranslatef
    0.41
     महत्त्व
    0.40
     Breakthrough
    0.40
    杲
    0.40
     Registrar
    0.40
     Percent
    0.39
     Berkeley
    0.39
     Successful
    0.39
     Motorola
    0.39
    POSITIVE LOGITS
     shenanigans
    0.51
     actuaciones
    0.50
    ijen
    0.45
    UNICATIONS
    0.44
    का
    0.44
    jene
    0.44
    ło
    0.42
     actuación
    0.41
    assers
    0.41
    🤯
    0.41
    Activations Density 0.000%

    No Known Activations