© 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. 79307
    Prev
    Next
    INDEX
    Explanations

    skills, Saturday, online, tickets, remastered

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

    steps, girl, enjoy, miss

    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
    ꔰ
    0.47
    だった
    0.46
     જાણ
    0.45
    attham
    0.44
     avait
    0.44
     গ্রাহ
    0.44
    痤
    0.44
    Bună
    0.44
     zat
    0.43
    兌
    0.43
    POSITIVE LOGITS
    m
    0.45
     wakeup
    0.45
     Sunflower
    0.43
     surprises
    0.42
     departure
    0.41
    network
    0.41
     surprise
    0.41
    CH
    0.40
     intertw
    0.40
    говор
    0.39
    Activations Density 0.001%

    No Known Activations