© 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. 3337
    Prev
    Next
    INDEX
    Explanations

    license, copyright, software foundation

    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
     litoral
    -0.88
    crate
    -0.80
    Queen
    -0.79
     elde
    -0.78
    speed
    -0.77
    twór
    -0.76
     tänker
    -0.76
    lipo
    -0.76
    ге
    -0.75
     peso
    -0.75
    POSITIVE LOGITS
     manag
    0.97
     필요
    0.89
    dada
    0.87
     invitamos
    0.84
     exemplu
    0.84
    bomba
    0.83
    Ina
    0.83
     chall
    0.82
    indrome
    0.81
    Caro
    0.81
    Activations Density 0.000%

    No Known Activations