© 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. 124639
    Prev
    Next
    INDEX
    Explanations

    DIY, preparation, after conjunctions

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

    foreign language text and descriptions

    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
    ²/
    0.48
     perny
    0.44
     siempre
    0.42
     ²
    0.42
     excepc
    0.42
     alluded
    0.42
    ²
    0.41
    alupe
    0.41
     али
    0.41
    ².
    0.40
    POSITIVE LOGITS
     ತಯಾರ
    0.48
     প্রস্তুত
    0.46
     গোয়
    0.46
    幄
    0.46
     ไล
    0.46
     เตรียม
    0.45
     চারি
    0.44
     조합
    0.43
     DIY
    0.43
     Observation
    0.43
    Activations Density 0.000%

    No Known Activations