© 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. 88229
    Prev
    Next
    INDEX
    Explanations

    meuble tv pas cher

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

    variations

    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
    ad
    0.52
    than
    0.52
    com
    0.51
    n
    0.48
    avan
    0.47
    nian
    0.47
    ir
    0.47
    in
    0.47
    kath
    0.45
    dance
    0.45
    POSITIVE LOGITS
     запад
    0.49
     suport
    0.46
    сно
    0.46
    мол
    0.46
    ૂ
    0.46
    зел
    0.45
    хал
    0.45
     esist
    0.45
    ーツ
    0.44
    сності
    0.44
    Activations Density 0.007%

    No Known Activations