© 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. 190594
    Prev
    Next
    INDEX
    Explanations

    foreign languages

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

    feature selection, deductive reasoning, relative terms

    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
     ऐसे
    0.49
     MK
    0.48
     Capri
    0.46
     सांप
    0.44
     sprawl
    0.43
     이러한
    0.42
     такого
    0.42
     I
    0.41
     하나의
    0.40
    wide
    0.40
    POSITIVE LOGITS
    間
    0.57
    وري
    0.57
    ଦ
    0.57
    يل
    0.55
    ிய
    0.55
    ဈ
    0.55
    λει
    0.54
    ରା
    0.54
    ستخدم
    0.53
     gebruikt
    0.52
    Activations Density 0.001%

    No Known Activations