© 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. 99389
    Prev
    Next
    INDEX
    Explanations

    specific events and processes

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

    violence, murder, action

    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
    ckiej
    0.50
     угро
    0.49
     Wechsler
    0.48
    picode
    0.48
    ер
    0.47
    郸
    0.47
     праздник
    0.47
    colorControl
    0.47
    कालिक
    0.47
     이상의
    0.46
    POSITIVE LOGITS
    irt
    0.45
    女士
    0.45
    叶
    0.45
     mM
    0.45
    ्याज
    0.44
    टेन
    0.42
     isEmpty
    0.42
    Pharmaceutical
    0.42
    Technology
    0.41
     قامت
    0.41
    Activations Density 0.000%

    No Known Activations