© 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. 113682
    Prev
    Next
    INDEX
    Explanations

    writing lists

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

    explaining my programming

    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
    timeStamp
    0.46
    דם
    0.44
     restores
    0.42
     BROAD
    0.42
     WORTH
    0.42
     EXTER
    0.42
    }}(
    0.41
     }}(
    0.41
     axles
    0.41
     ess
    0.40
    POSITIVE LOGITS
    ureau
    0.52
    北大
    0.49
    ២
    0.48
    Selecion
    0.48
    制限
    0.47
    複数
    0.47
    第二百
    0.47
    Perf
    0.47
     scène
    0.47
    évolution
    0.47
    Activations Density 0.001%

    No Known Activations