© 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. 245674
    Prev
    Next
    INDEX
    Explanations

    legal and financial 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
     idempotent
    0.45
     factories
    0.44
    '
    0.43
     into
    0.41
    いません
    0.41
     editors
    0.41
    Mutex
    0.41
     rate
    0.41
     centers
    0.41
    /
    0.41
    POSITIVE LOGITS
     situação
    0.49
     situación
    0.47
     स्पेश
    0.46
     schönen
    0.45
     जश्न
    0.45
     schöne
    0.45
     चमकदार
    0.45
     الحاج
    0.43
     ओह
    0.43
     mooie
    0.42
    Activations Density 0.000%

    No Known Activations