© 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. 237109
    Prev
    Next
    INDEX
    Explanations

    following year, business accounts, charity fundraiser, committed lifestyle

    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
    Understand
    0.52
    Preferred
    0.52
    ྪ
    0.51
    Vik
    0.50
     シェ
    0.50
     ベ
    0.49
    亓
    0.49
    ฉ
    0.48
    ᑯ
    0.48
     Bucs
    0.47
    POSITIVE LOGITS
    ента
    0.46
    様専用
    0.46
     henceforth
    0.45
     forfait
    0.45
     fermentation
    0.45
     '+'
    0.44
     plotting
    0.44
     artinya
    0.44
    authier
    0.44
    ab
    0.43
    Activations Density 0.001%

    No Known Activations