© 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. 40773
    Prev
    Next
    INDEX
    Explanations

    Yeah

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

    not malicious or hostile

    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
     veloce
    0.55
    Για
    0.52
    Ј
    0.49
    Μ
    0.46
    Ε
    0.46
     thrombocyt
    0.46
    Յ
    0.45
    鬚
    0.45
     initials
    0.45
    Ῥ
    0.45
    POSITIVE LOGITS
     العالمين
    0.51
     UFO
    0.44
     பக்கம்
    0.43
     Ed
    0.43
    statusCode
    0.43
     生活
    0.43
    dens
    0.42
    ধ্যে
    0.42
     Daytona
    0.42
    ımı
    0.42
    Activations Density 0.000%

    No Known Activations