© 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. 48676
    Prev
    Next
    INDEX
    Explanations

    limit of

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

    even sometimes

    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
    knię
    0.45
    ולים
    0.44
    toys
    0.42
    toMap
    0.42
    crawler
    0.42
    tab
    0.42
    kart
    0.42
    聂
    0.42
    dbl
    0.41
    жан
    0.41
    POSITIVE LOGITS
     sometimes
    0.47
     in
    0.46
     amelior
    0.44
     في
    0.44
     manger
    0.44
     anisotropy
    0.42
     bús
    0.42
     intermittently
    0.42
     postures
    0.42
     interplay
    0.41
    Activations Density 0.000%

    No Known Activations