© 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. 91858
    Prev
    Next
    INDEX
    Explanations

    Success, ultimate, lessons

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

    not just about

    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
     продолжи
    0.50
     Pandas
    0.48
     গড়ে
    0.48
     McMaster
    0.47
     ψ
    0.47
    翛
    0.47
     რა
    0.46
     Psik
    0.46
    ⋆
    0.46
     состави
    0.46
    POSITIVE LOGITS
    ريع
    0.55
    endre
    0.51
    you
    0.50
    收益
    0.49
     allergy
    0.47
    se
    0.46
    油
    0.45
    Retrieve
    0.44
    income
    0.44
    Enable
    0.44
    Activations Density 0.000%

    No Known Activations