© 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. 189679
    Prev
    Next
    INDEX
    Explanations

    Default bid

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

    thinking outside

    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
     $
    0.50
    efore
    0.49
     omega
    0.49
     三
    0.48
     i
    0.47
     zir
    0.46
     dk
    0.46
     З
    0.46
     chiar
    0.45
     zwią
    0.45
    POSITIVE LOGITS
    撷
    0.47
    reuse
    0.46
    रों
    0.46
    सन्
    0.45
    మన
    0.45
    忔
    0.44
     Footage
    0.43
     ছুটে
    0.43
    íqu
    0.43
    मधील
    0.43
    Activations Density 0.002%

    No Known Activations