© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32275
    Prev
    Next
    INDEX
    Explanations

    fetching or retrieving data

    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
    thmetic
    -0.89
    citroen
    -0.88
    gmd
    -0.87
    orithm
    -0.86
    ומית
    -0.84
    razer
    -0.84
    kulu
    -0.80
    othesis
    -0.77
     kesi
    -0.77
    corollary
    -0.76
    POSITIVE LOGITS
    aps
    0.79
    aga
    0.77
     flowery
    0.76
     Oba
    0.75
     upholstered
    0.74
    ags
    0.71
    VisualStyle
    0.70
     podamos
    0.70
    reihe
    0.69
    يًا
    0.69
    Activations Density 0.025%

    No Known Activations