© 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. 5754
    Prev
    Next
    INDEX
    Explanations

    organizational concepts and measurements

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

    handling, development, comprehension, loop

    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
    ۵
    0.38
     Abhäng
    0.36
    ۷
    0.35
     servidor
    0.35
     verschiedenen
    0.34
     sauvegard
    0.34
    ശ്വാ
    0.32
     traité
    0.32
     Méd
    0.32
     Przed
    0.32
    POSITIVE LOGITS
    ING
    0.38
    тың
    0.38
    、
    0.35
    ®,
    0.33
    。
    0.33
     extraordinaire
    0.31
     보다
    0.30
    หรือ
    0.30
     және
    0.29
    )。
    0.29
    Activations Density 2.160%

    No Known Activations