© 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. 199679
    Prev
    Next
    INDEX
    Explanations

    save, Texas, still, ought, best

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

    man, dude, while

    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
     Tubes
    0.50
     ry
    0.50
     Ry
    0.49
     少し
    0.46
     Hera
    0.46
     Air
    0.45
     很
    0.44
     नमी
    0.44
     ఎంత
    0.44
    at
    0.43
    POSITIVE LOGITS
     hoạt
    0.49
     advocacy
    0.46
     činn
    0.46
     hoạch
    0.45
    យើង
    0.45
     đỡ
    0.44
    ++;
    0.43
     działal
    0.43
    맨
    0.43
     támogat
    0.42
    Activations Density 0.000%

    No Known Activations