© 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. 106000
    Prev
    Next
    INDEX
    Explanations

    specific contexts

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

    refusing harmful content

    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
    ိုး
    0.43
    〒
    0.42
    手段
    0.41
    そう
    0.41
    堺
    0.40
    なの
    0.39
    σεις
    0.39
    <0xE3>
    0.38
    ိုလ်
    0.38
    ObjectURL
    0.38
    POSITIVE LOGITS
    ED
    0.55
     ferocious
    0.51
    ed
    0.50
    ünschen
    0.50
     వార
    0.49
     Eurasian
    0.49
     Schum
    0.48
     fondos
    0.48
     குறித்த
    0.48
    ER
    0.47
    Activations Density 0.001%

    No Known Activations