© 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. 17555
    Prev
    Next
    INDEX
    Explanations

    inaugurate, zoot suit, washing pools, power point

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

    computationally expensive

    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
     организма
    0.33
    ত্ত
    0.32
     정의역
    0.32
    ratulations
    0.31
     জীববিজ্ঞান
    0.31
    贋
    0.31
    NSInteger
    0.30
     presenceData
    0.30
     ฝึก
    0.30
    มาชิก
    0.30
    POSITIVE LOGITS
     a
    0.35
     (
    0.35
     Tram
    0.33
     cables
    0.32
     wipers
    0.31
     accessoires
    0.31
     Fender
    0.31
     tram
    0.30
     Straße
    0.30
     occasionally
    0.30
    Activations Density 0.001%

    No Known Activations