© 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. 138495
    Prev
    Next
    INDEX
    Explanations

    route in, located in

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

    experience followed by list instructions

    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
     juniors
    0.46
    良好的
    0.46
    netHex
    0.46
     રહેશે
    0.45
     pourcentage
    0.45
     artificielle
    0.45
    \})
    0.44
     solicitation
    0.43
    程序的
    0.43
     signatures
    0.43
    POSITIVE LOGITS
    in
    0.46
     replace
    0.45
    ar
    0.45
    🦅
    0.44
    ittings
    0.44
    ı
    0.42
     х
    0.42
     mord
    0.42
    ть
    0.41
    :
    0.41
    Activations Density 0.000%

    No Known Activations