© 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. 241920
    Prev
    Next
    INDEX
    Explanations

    victory, won, next, Shop, Olympic

    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
    裘
    0.50
    ogener
    0.48
    urtle
    0.47
     mulig
    0.46
    embryon
    0.46
     mux
    0.46
    投资基金
    0.45
     impoz
    0.45
     Fourteenth
    0.44
     фонд
    0.44
    POSITIVE LOGITS
    ک
    0.53
    کار
    0.51
    Sz
    0.49
    Για
    0.47
    SANIT
    0.47
    SAN
    0.47
    Ng
    0.46
     ڈاک
    0.46
    ીર
    0.45
    𝗨
    0.45
    Activations Density 0.000%

    No Known Activations