© 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. 123129
    Prev
    Next
    INDEX
    Explanations

    expectations, performance, analysis

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

    algorithm for, classical music, positive integers

    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
    download
    0.49
     rotting
    0.48
     긴
    0.47
     약간
    0.47
    tau
    0.47
    dim
    0.47
    ripcion
    0.47
    buy
    0.45
    cstdio
    0.45
     움
    0.45
    POSITIVE LOGITS
     непосред
    0.49
    宒
    0.47
    QUE
    0.46
    FR
    0.43
    に対
    0.42
    畕
    0.42
    DR
    0.42
    AT
    0.41
    宏
    0.41
    ানন্দ
    0.41
    Activations Density 0.001%

    No Known Activations