© 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. 96659
    Prev
    Next
    INDEX
    Explanations

    Camden Yards, efficient pacing, EDC

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

    alternative vocabulary and synonyms

    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
     moest
    0.49
    UserId
    0.43
    ost
    0.42
    จะเป็น
    0.41
    你就
    0.41
    输入的
    0.41
    핵
    0.41
     필수
    0.41
     거기
    0.40
    如下
    0.40
    POSITIVE LOGITS
     meilleur
    0.50
    ف
    0.47
     réussir
    0.47
    ম
    0.47
    Diameter
    0.46
    BH
    0.44
    Hours
    0.44
    য়
    0.44
     benchmark
    0.44
    י
    0.43
    Activations Density 0.000%

    No Known Activations