© 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. 76814
    Prev
    Next
    INDEX
    Explanations

    state updates with useState

    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
     निशाने
    0.40
    ynie
    0.40
     Pharmacology
    0.39
     intramuscular
    0.39
    ۴
    0.39
    :";
    0.38
    म्प्ट
    0.38
     முன்ன
    0.38
    junctive
    0.38
    頷
    0.38
    POSITIVE LOGITS
    Stepper
    0.42
    S
    0.41
     /
    0.41
    ulele
    0.40
     العالمي
    0.40
    v
    0.39
     purify
    0.39
    កំណត់
    0.39
    Definition
    0.38
    brad
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.