© 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. 224263
    Prev
    Next
    INDEX
    Explanations

    dumpster, opportunity, probe, provide

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

    non-English words or specific contexts

    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
    small
    0.51
    دو
    0.48
     Phase
    0.47
    i
    0.47
    P
    0.47
    Pra
    0.46
     Product
    0.46
     Small
    0.45
    Phase
    0.45
    Product
    0.44
    POSITIVE LOGITS
     объеди
    0.55
     музи
    0.51
     እነ
    0.50
     ಉತ್
    0.49
     संस्कृति
    0.49
     раду
    0.48
     များ
    0.48
     僕
    0.48
     twórc
    0.48
    ྣ
    0.48
    Activations Density 0.000%

    No Known Activations