© 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. 48736
    Prev
    Next
    INDEX
    Explanations

    legal or business terms

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

    Important considerations, mimicking, masterpiece

    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
    aglio
    0.53
     पैक
    0.51
    ieger
    0.50
    ikke
    0.50
    nacht
    0.48
     댓글
    0.48
     ด
    0.47
     คลิ
    0.47
     হুগলী
    0.47
     پھر
    0.47
    POSITIVE LOGITS
    WT
    0.50
    ETO
    0.46
    ET
    0.46
    CAF
    0.45
    SELF
    0.44
    Special
    0.44
    WE
    0.43
    CASE
    0.43
    VARCHAR
    0.43
    ’
    0.42
    Activations Density 0.000%

    No Known Activations