© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30224
    Prev
    Next
    INDEX
    Explanations

    names ending in rs or ars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iants
    -0.82
    ix
    -0.77
    pec
    -0.75
    tizen
    -0.74
    ecas
    -0.74
     LIM
    -0.74
    setFont
    -0.73
    Ƶ
    -0.73
     партии
    -0.73
    hark
    -0.73
    POSITIVE LOGITS
    ening
    0.86
     bars
    0.81
    ened
    0.77
    migo
    0.75
    RTDA
    0.73
    ்ச
    0.73
    ומ
    0.72
    Buildable
    0.72
     Bars
    0.70
    ازات
    0.70
    Activations Density 0.036%

    No Known Activations