© 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. 55539
    Prev
    Next
    INDEX
    Explanations

    strike, bar, was, of, frame

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

    harmful content requests

    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
     ઉજ
    0.51
    小伙伴
    0.47
    公平
    0.46
    行う
    0.46
     injuring
    0.45
    lás
    0.45
    lar
    0.44
    匆
    0.44
    ilar
    0.44
    lari
    0.43
    POSITIVE LOGITS
    っしゃ
    0.51
     இந்தக்
    0.41
     ouvre
    0.40
     instinct
    0.40
    ี
    0.40
     academically
    0.39
    واه
    0.39
     hahaha
    0.39
    jalpha
    0.39
     sublimation
    0.38
    Activations Density 0.000%

    No Known Activations