© 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. 32148
    Prev
    Next
    INDEX
    Explanations

    for [noun/phrase]

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

    beat drops

    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
    plet
    0.50
    ਕ
    0.49
     செயல்பா
    0.48
    ſelf
    0.46
     DURING
    0.46
    ſe
    0.46
    出
    0.45
    oused
    0.44
    ல்
    0.44
    嶈
    0.44
    POSITIVE LOGITS
     特に
    0.56
    PropertyParam
    0.48
    henti
    0.47
     Racing
    0.45
    ።
    0.44
     Chinatown
    0.44
     RFP
    0.43
    ริม
    0.43
     hatchery
    0.42
     Nunes
    0.42
    Activations Density 0.000%

    No Known Activations