© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9179
    Prev
    Next
    INDEX
    Explanations

    V words like Vibe, Volcanic, Volatility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    a
    0.71
    ِّف
    0.63
    기
    0.62
    in
    0.62
    മ്ബ
    0.62
    n
    0.62
    ij
    0.60
    ir
    0.59
    it
    0.59
    liquidacion
    0.59
    POSITIVE LOGITS
    '
    1.36
    0.81
    (
    0.66
                    
    0.65
    对
    0.64
    /
    0.63
     V
    0.61
    "
    0.61
    ко
    0.61
    V
    0.61
    Activations Density 0.378%

    No Known Activations