© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204356
    Prev
    Next
    INDEX
    Explanations

    UPI, affected spinal, famous reproductions

    np_acts-logits-general · gemini-2.5-flash-lite

    crucial points, markets, expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    宿
    0.44
    、
    0.44
    Spread
    0.43
    норийска
    0.42
    ev
    0.42
    生理
    0.42
    hock
    0.42
    pass
    0.42
     Spread
    0.41
    collar
    0.41
    POSITIVE LOGITS
     certamente
    0.50
     fratello
    0.49
     gruppi
    0.48
     punctuation
    0.48
    ীরে
    0.48
     solusi
    0.48
    밋
    0.47
     profond
    0.47
    িত্ব
    0.47
     zespo
    0.46
    Activations Density 0.000%

    No Known Activations