© 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. 50139
    Prev
    Next
    INDEX
    Explanations

    Regulatory commission

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

    penetration testing, control systems, stewardship

    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
    и
    0.49
     Cortana
    0.43
    ndash
    0.42
     asshole
    0.42
    ään
    0.42
     сфер
    0.42
     OTC
    0.41
    /*
    0.41
    спи
    0.41
     círculo
    0.41
    POSITIVE LOGITS
    Were
    0.46
     niew
    0.45
    COOK
    0.44
    BNA
    0.44
    WIL
    0.43
     بنائے
    0.43
    Clothing
    0.42
    Ẫ
    0.42
     تھے
    0.42
     লিপিবদ্ধ
    0.42
    Activations Density 0.000%

    No Known Activations