© 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. 101459
    Prev
    Next
    INDEX
    Explanations

    winds returned

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

    suggest better explanations

    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
    醚
    0.46
     terima
    0.42
    িন্দু
    0.42
     lysosomes
    0.40
    सर्ग
    0.39
     aldehyde
    0.39
     emitters
    0.39
     noirs
    0.38
     maquillaje
    0.38
    engkap
    0.38
    POSITIVE LOGITS
    #$%
    0.46
    (
    0.44
    sdf
    0.42
     شدید
    0.42
    }",
    0.41
     مست
    0.41
     frustration
    0.40
    
    0.40
    に基づいて
    0.39
    のですが
    0.39
    Activations Density 0.001%

    No Known Activations