© 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. 157237
    Prev
    Next
    INDEX
    Explanations

    Andorra, our week, but, Note, including, even

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

    progress & specific tags

    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
     Packs
    0.49
     Disbursements
    0.46
     ／
    0.46
     Successful
    0.45
     Prerequisites
    0.43
    ⁾
    0.43
     Decorations
    0.43
     സ
    0.42
     Immediate
    0.41
     ದ
    0.41
    POSITIVE LOGITS
    ской
    0.48
    IS
    0.46
    ONES
    0.45
    ఎస్
    0.44
    شارك
    0.44
    Э
    0.44
    фов
    0.43
    F
    0.43
    town
    0.43
    рс
    0.43
    Activations Density 0.001%

    No Known Activations