© 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. 108021
    Prev
    Next
    INDEX
    Explanations

    sd card

    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
    freiheit
    -0.81
     Vì
    -0.77
     thermal
    -0.77
     Actividades
    -0.77
     ufficiale
    -0.75
     enzyme
    -0.75
     Inequalities
    -0.74
     Olympics
    -0.73
    原始内容
    -0.73
    岁
    -0.72
    POSITIVE LOGITS
    Fat
    0.85
    FAT
    0.85
     FAT
    0.84
     Fat
    0.84
    鄱
    0.80
    sector
    0.77
     Тол
    0.77
     fat
    0.75
    polis
    0.75
    phat
    0.75
    Activations Density 0.003%

    No Known Activations