© 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. 58854
    Prev
    Next
    INDEX
    Explanations

    good horse

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

    conditional or exceptions

    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
    初の
    0.45
    Р
    0.45
     изпъл
    0.44
     funzione
    0.43
     მე
    0.43
     июля
    0.41
     реб
    0.41
    Л
    0.41
     اختیار
    0.40
    ın
    0.40
    POSITIVE LOGITS
    物語
    0.42
     unfairly
    0.41
     Woot
    0.40
     baya
    0.39
    vann
    0.39
     Maul
    0.38
     Wür
    0.38
     fidel
    0.38
    vur
    0.38
    asshi
    0.38
    Activations Density 0.000%

    No Known Activations