© 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. 48822
    Prev
    Next
    INDEX
    Explanations

    save Elena

    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
    戦う
    -0.76
     vectoriales
    -0.75
     Albu
    -0.75
    赋
    -0.75
    滯
    -0.73
     restitu
    -0.70
    Vá
    -0.70
    battles
    -0.69
     مو
    -0.69
     Nieuwe
    -0.69
    POSITIVE LOGITS
     survivor
    1.45
     survivors
    1.34
     Survivors
    1.32
     Survivor
    1.23
    Survivors
    1.04
    dbd
    0.96
     sobrevi
    0.92
     Mori
    0.89
    survi
    0.88
    Survivor
    0.88
    Activations Density 0.003%

    No Known Activations