© 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. 32223
    Prev
    Next
    INDEX
    Explanations

    automotive bumpers

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

    no runtime overhead

    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
     Maldonado
    0.49
    ținut
    0.48
     Taş
    0.47
    nav
    0.46
    O
    0.46
     natu
    0.45
    ছার
    0.45
     Nuovo
    0.44
    zac
    0.44
     Camacho
    0.44
    POSITIVE LOGITS
    ли
    0.45
     импе
    0.45
    '،
    0.44
    较高
    0.44
     ۲
    0.44
    约为
    0.44
     մե
    0.43
    高い
    0.42
     թ
    0.42
    ة
    0.42
    Activations Density 0.001%

    No Known Activations