© 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. 173155
    Prev
    Next
    INDEX
    Explanations

    got a

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

    delivering peace of mind

    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
    [*
    0.48
     bosques
    0.47
    リム
    0.46
     Mou
    0.46
    গ্র
    0.45
    牆
    0.44
    スン
    0.44
    テール
    0.44
    市值
    0.44
    itale
    0.44
    POSITIVE LOGITS
     मृत्यु
    0.57
     पड़ेंगे
    0.46
    </blockquote>
    0.45
     według
    0.45
     कार्यकारिणी
    0.45
     waardoor
    0.45
     गए
    0.45
     приве
    0.45
    的情况
    0.44
     ติด
    0.44
    Activations Density 0.001%

    No Known Activations