© 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. 23544
    Prev
    Next
    INDEX
    Explanations

    months, hauling, seemed, required, delicious, why

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

    mind, head, cravings, sun

    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
    に伴
    0.46
     صد
    0.46
     ती
    0.46
    겪
    0.46
     Fresnel
    0.45
     風
    0.45
    系の
    0.45
    .}(
    0.44
     Hương
    0.44
     ச
    0.44
    POSITIVE LOGITS
    ronaut
    0.54
     باسکٹ
    0.50
    onaut
    0.45
     astronaut
    0.44
    ួក
    0.44
    averaged
    0.44
    槳
    0.44
    เร็จ
    0.44
    emergency
    0.43
     emergency
    0.43
    Activations Density 0.000%

    No Known Activations