© 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. 169856
    Prev
    Next
    INDEX
    Explanations

    Dangerous As Sin

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

    code keywords and identifiers

    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
    ផ្ត
    0.49
    toires
    0.48
    то
    0.47
    vér
    0.46
     inept
    0.46
    𝚟
    0.46
    ам
    0.46
    ニャ
    0.46
    न
    0.45
     abusive
    0.45
    POSITIVE LOGITS
     yıll
    0.46
    Pat
    0.44
    Days
    0.43
    Mobil
    0.42
    FOLLOW
    0.42
    ابی
    0.42
    Jen
    0.42
    TG
    0.42
    
    0.42
    Cargo
    0.40
    Activations Density 0.001%

    No Known Activations