© 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. 70146
    Prev
    Next
    INDEX
    Explanations

    general nouns and phrases

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

    harming someone

    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
    args
    0.50
    .
    0.49
     وزير
    0.48
    IL
    0.46
     அவ்
    0.46
    licer
    0.46
     nose
    0.46
    Apps
    0.46
    othic
    0.45
    '"
    0.45
    POSITIVE LOGITS
    انگ
    0.47
    ان
    0.46
    ر
    0.46
    گیر
    0.45
    спользу
    0.45
     ಸುರ
    0.45
    ಝ
    0.45
     अधिक
    0.44
     Zack
    0.44
    नून
    0.44
    Activations Density 0.000%

    No Known Activations