© 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. 219282
    Prev
    Next
    INDEX
    Explanations

    your warehouse

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

    core principles and guidelines

    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
    遥
    0.53
    音が
    0.48
    мато
    0.46
     nhấn
    0.46
    명이
    0.46
    琰
    0.45
    ва
    0.45
    ลม
    0.45
    啥
    0.45
    யில
    0.44
    POSITIVE LOGITS
    timeStamp
    0.49
     特許
    0.49
    subnet
    0.48
    band
    0.47
    targetContext
    0.47
    "—
    0.47
    បង្កើត
    0.46
    ###############
    0.46
    preset
    0.45
     Potenz
    0.44
    Activations Density 0.000%

    No Known Activations