© 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. 198080
    Prev
    Next
    INDEX
    Explanations

    clinic donations

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

    security communication, locations, primitives, combinations

    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
    Ö
    0.52
    Desde
    0.52
    serializer
    0.51
    Japanese
    0.49
    Basically
    0.49
    İstanbul
    0.49
    kü
    0.48
    Ä
    0.48
    Encript
    0.47
    Ü
    0.47
    POSITIVE LOGITS
     donate
    0.50
     clinic
    0.49
    ビン
    0.48
     pell
    0.48
     tann
    0.47
     Clinic
    0.46
     pea
    0.45
     accumulate
    0.45
     bho
    0.45
     biomedical
    0.45
    Activations Density 0.000%

    No Known Activations