© 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. 152219
    Prev
    Next
    INDEX
    Explanations

    "royal plant" basil botanist

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

    conversion of energy or matter

    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
    गुरु
    0.55
    Авто
    0.54
    сіб
    0.52
    gave
    0.51
    ఠ
    0.51
     контек
    0.50
    Bună
    0.49
    हार्
    0.48
     kling
    0.47
    Gö
    0.47
    POSITIVE LOGITS
     生産
    0.47
     mamy
    0.47
     מש
    0.45
     minted
    0.45
     praised
    0.44
     doesn
    0.44
    အချိန်
    0.44
    ("~/
    0.43
     e
    0.43
     listings
    0.43
    Activations Density 0.001%

    No Known Activations