© 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. 216366
    Prev
    Next
    INDEX
    Explanations

    combining information

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

    drafting emails and focusing

    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
    ೆ
    0.51
    데이
    0.49
     Кі
    0.49
     Shareholders
    0.48
     strengthens
    0.47
    ને
    0.47
     shareholders
    0.47
    bk
    0.47
     Wife
    0.46
    एच
    0.46
    POSITIVE LOGITS
     ismi
    0.44
    万
    0.44
     maze
    0.43
     udziel
    0.41
    因为它
    0.41
     имена
    0.40
     tweak
    0.39
    irittura
    0.39
    杨
    0.38
     propositional
    0.38
    Activations Density 0.000%

    No Known Activations