© 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. 112957
    Prev
    Next
    INDEX
    Explanations

    actions leading to a purpose

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

    converting to percentage

    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
     চাঁ
    0.43
     Rookie
    0.42
    хие
    0.42
    牛
    0.42
    ('_
    0.42
    NEW
    0.41
    沙漠
    0.40
    헬
    0.40
    实践
    0.40
     سلامه
    0.40
    POSITIVE LOGITS
    ant
    0.47
    ori
    0.45
    swering
    0.44
    uar
    0.43
    ugar
    0.43
    ير
    0.42
    ilien
    0.41
    getError
    0.41
    setError
    0.41
    akin
    0.41
    Activations Density 0.000%

    No Known Activations