© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63292
    Prev
    Next
    INDEX
    Explanations

    guide or announcement beginnings

    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
    Mall
    -0.80
     Ahmedabad
    -0.80
    План
    -0.79
    ária
    -0.74
    Teléfono
    -0.73
     Duluth
    -0.73
     erweit
    -0.72
    ablon
    -0.71
     СПб
    -0.71
     Lublin
    -0.71
    POSITIVE LOGITS
    Queensland
    0.77
    ACT
    0.76
    hella
    0.76
     Elie
    0.75
    grou
    0.75
    酌
    0.74
     CHARACTERS
    0.74
     danno
    0.73
     grou
    0.73
    forces
    0.72
    Activations Density 0.005%

    No Known Activations