© 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. 74407
    Prev
    Next
    INDEX
    Explanations

    German place names and programming syntax

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

    closing parenthesis

    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
    լ
    0.44
    贈
    0.44
    如果有
    0.41
     conviction
    0.41
    ंट
    0.41
    லி
    0.41
    に使
    0.40
    喧
    0.40
    级别的
    0.40
    트로
    0.40
    POSITIVE LOGITS
     Kedua
    0.48
     Winchester
    0.44
     FEL
    0.43
     allemand
    0.42
    yin
    0.42
     Allemagne
    0.41
     Touring
    0.40
     Allegheny
    0.40
     Arnhem
    0.40
     alemán
    0.39
    Activations Density 0.000%

    No Known Activations