© 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. 172475
    Prev
    Next
    INDEX
    Explanations

    brands and descriptive words

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

    comparing models and their strengths

    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
    重
    0.50
     yat
    0.46
     bursts
    0.45
    ied
    0.45
    ibrate
    0.44
     intensive
    0.43
    原始内容存档于
    0.43
    தி
    0.43
     bilateral
    0.42
     lavoro
    0.42
    POSITIVE LOGITS
     चॉकलेट
    0.47
    ल्फी
    0.46
    菈
    0.44
    loé
    0.44
    摟
    0.43
    LOUIS
    0.43
     উপভোগ
    0.42
    Rap
    0.42
     उपभोक्ताओं
    0.42
    lia
    0.41
    Activations Density 0.001%

    No Known Activations