© 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. 17426
    Prev
    Next
    INDEX
    Explanations

    slurred speech / 20 January

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

    riddles, "what am i"

    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
    瑛
    0.40
    琊
    0.40
     titleImageUrl
    0.39
    پيديا
    0.38
     uart
    0.38
    atthaya
    0.38
     جنوب
    0.37
     বন্দরে
    0.37
     énon
    0.37
    湄
    0.36
    POSITIVE LOGITS
    “
    0.43
    r
    0.36
     .
    0.35
      
    0.35
     Helic
    0.35
    h
    0.33
     “
    0.33
    ç
    0.33
     ,
    0.32
     drink
    0.32
    Activations Density 0.429%

    No Known Activations