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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90553
    Prev
    Next
    INDEX
    Explanations

    ServiceStack or email addresses

    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
     Used
    -0.79
     assuming
    -0.77
     little
    -0.76
     impression
    -0.75
     impresion
    -0.73
     乗
    -0.71
    母の
    -0.71
     implicit
    -0.69
    zionali
    -0.69
     laufen
    -0.69
    POSITIVE LOGITS
    Stack
    0.84
    stak
    0.82
     energe
    0.82
    烂
    0.82
    ା
    0.80
    instr
    0.79
     Stacks
    0.79
    LANE
    0.78
     Fingerprint
    0.78
    嬢
    0.77
    Activations Density 0.036%

    No Known Activations