© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 83868
    Prev
    Next
    INDEX
    Explanations

    allow pass signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perspekt
    0.40
    갸
    0.40
    ั่น
    0.39
    وكب
    0.39
    ηγ
    0.38
    ाइक
    0.38
    貥
    0.38
     traduction
    0.37
     Transl
    0.37
     dibujar
    0.37
    POSITIVE LOGITS
     Bilal
    0.43
    woman
    0.40
     woman
    0.39
     lungo
    0.38
     Woman
    0.38
     diverted
    0.38
     Lac
    0.37
    ୈ
    0.37
    )}}{
    0.37
    bestos
    0.37
    Activations Density 0.000%

    No Known Activations