© 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. 208259
    Prev
    Next
    INDEX
    Explanations

    route when

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

    capt, rolling, Backend, faction

    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
     Filters
    0.54
    摹
    0.48
     bă
    0.48
    늡
    0.47
     bá
    0.47
     Filter
    0.47
    拴
    0.46
     Führung
    0.45
     vă
    0.44
     leren
    0.43
    POSITIVE LOGITS
     accurately
    0.48
    meter
    0.48
    lightning
    0.47
    mid
    0.47
    :\
    0.46
    कोण
    0.46
    -(\
    0.46
    Lil
    0.46
    リューム
    0.46
    metre
    0.45
    Activations Density 0.000%

    No Known Activations