© 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. 206326
    Prev
    Next
    INDEX
    Explanations

    model pattern

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

    knock, plants, studying, tall, random, sound

    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
    및
    0.55
    리와
    0.52
    และความ
    0.50
    এবং
    0.48
     उपकरणों
    0.46
    ického
    0.45
    और
    0.45
    ukung
    0.45
     चलाई
    0.45
     यूट्यूब
    0.44
    POSITIVE LOGITS
    ).
    0.50
    .)
    0.48
    .
    0.48
    。
    0.45
    ."
    0.45
     at
    0.44
     from
    0.42
     diabetic
    0.41
     notified
    0.41
     category
    0.41
    Activations Density 0.005%

    No Known Activations