© 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. 112443
    Prev
    Next
    INDEX
    Explanations

    and gifts

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

    supply chain visibility audits

    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
     settimana
    0.58
    ड्डा
    0.54
    વાથી
    0.53
     domenica
    0.52
    ammlung
    0.52
    İstanbul
    0.52
     săptăm
    0.50
    Ḫ
    0.50
    Chào
    0.48
    Grazie
    0.48
    POSITIVE LOGITS
     shrink
    0.50
    belt
    0.48
    ULE
    0.47
    ule
    0.46
     belts
    0.46
    عي
    0.45
     decompose
    0.43
     refine
    0.43
     fuel
    0.43
     belt
    0.42
    Activations Density 0.001%

    No Known Activations