© 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. 136124
    Prev
    Next
    INDEX
    Explanations

    Lord:magazines bylarge forgrim figurescompelling thanlatest sterilizer

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

    while / not

    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
    *
    0.48
     hard
    0.47
    -
    0.46
    <
    0.45
     branches
    0.43
     toward
    0.43
    )
    0.43
    /
    0.43
    Mb
    0.42
     hardwoods
    0.42
    POSITIVE LOGITS
     س
    0.57
     ಅನ
    0.52
     Dharm
    0.50
    縞
    0.50
     새
    0.50
     ಪರ
    0.50
     अंडरस्टैंड
    0.50
     بص
    0.49
     яким
    0.49
     اولیه
    0.48
    Activations Density 0.000%

    No Known Activations