© 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. 155523
    Prev
    Next
    INDEX
    Explanations

    word less code

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

    model response inicio "Okay"

    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
     ფორ
    0.46
     그거
    0.46
     급
    0.45
     బల
    0.45
     понимают
    0.45
    ೭
    0.44
    िक्स
    0.43
     ее
    0.43
    icki
    0.43
     happily
    0.43
    POSITIVE LOGITS
    مان
    0.50
    ا
    0.50
    decorators
    0.46
    ن
    0.46
    د
    0.45
    การ
    0.45
    ي
    0.44
     effetto
    0.43
    اك
    0.43
    مش
    0.43
    Activations Density 0.001%

    No Known Activations