© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 11696
    Prev
    Next
    INDEX
    Explanations

    questions and tips

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

    multi-language or capability descriptors

    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
    k
    0.47
    8
    0.46
    \
    0.45
    9
    0.44
    1
    0.44
    cię
    0.42
     unwitting
    0.42
    7
    0.41
    kaw
    0.40
     vicinity
    0.40
    POSITIVE LOGITS
     દરેક
    0.45
     चॉकलेट
    0.45
    其他
    0.44
    andled
    0.42
    abilität
    0.41
     ዘዴ
    0.41
     варто
    0.41
    ามารถ
    0.41
     sharpen
    0.41
    फ्त
    0.41
    Activations Density 0.000%

    No Known Activations