© 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. 158472
    Prev
    Next
    INDEX
    Explanations

    earned, your own app

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

    arctic tundra

    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
    v
    0.58
    conoc
    0.55
    rr
    0.53
    ef
    0.52
    p
    0.51
    í
    0.50
    w
    0.50
    f
    0.49
    ερ
    0.48
    erap
    0.48
    POSITIVE LOGITS
    (?:
    0.55
     comfy
    0.53
     ধাত
    0.50
     чтобы
    0.49
     හොඳ
    0.49
    㴬
    0.49
     تاکہ
    0.48
     좋아
    0.47
     কঠোর
    0.46
     عشان
    0.46
    Activations Density 0.002%

    No Known Activations