© 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. 97105
    Prev
    Next
    INDEX
    Explanations

    development, best,cousins,kids,way,regulate

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

    technical tools or browser

    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
    i
    0.56
     więc
    0.52
    ಿ
    0.43
     renewable
    0.43
     Tsche
    0.43
    nieuw
    0.43
     pł
    0.42
    itochond
    0.42
     ڕ
    0.42
     Rivera
    0.42
    POSITIVE LOGITS
    你自己
    0.55
     solucionar
    0.52
    恣
    0.49
    ्रेंस
    0.46
    你看
    0.46
     участке
    0.46
    Kep
    0.46
    शहर
    0.45
    ຜະລິດຕະພັນ
    0.45
    ড়াল
    0.44
    Activations Density 0.001%

    No Known Activations