© 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. 132958
    Prev
    Next
    INDEX
    Explanations

    processesdecisionssensitive aspects

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

    asteroid city

    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
     ट्रेनों
    0.48
     बनाएं
    0.46
     入っ
    0.45
     років
    0.45
     एक्सप्रेस
    0.42
     लेबल
    0.41
     촉
    0.40
     Passe
    0.39
     міні
    0.38
     됐
    0.38
    POSITIVE LOGITS
    ススメ
    0.55
    READY
    0.53
     singularities
    0.52
     growths
    0.49
     persiste
    0.47
     rallying
    0.46
     attends
    0.45
     accesses
    0.45
    并
    0.45
     infection
    0.45
    Activations Density 0.001%

    No Known Activations