© 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. 44794
    Prev
    Next
    INDEX
    Explanations

    down detector

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

    multilingual text options

    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
     రాజ్య
    0.44
     Saty
    0.43
     guerras
    0.43
     劉
    0.41
    Strings
    0.40
     Schrift
    0.40
     Liu
    0.40
     celebrations
    0.39
     Supporters
    0.39
     troupes
    0.39
    POSITIVE LOGITS
    फेक्ट
    0.55
    症状
    0.49
    ela
    0.48
    tså
    0.48
    냄
    0.48
    ov
    0.47
     fouling
    0.47
     ergonom
    0.47
     smelly
    0.47
    ovane
    0.47
    Activations Density 0.000%

    No Known Activations