© 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. 213028
    Prev
    Next
    INDEX
    Explanations

    saying "them"

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

    not funny

    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
     decomp
    0.50
    지만
    0.43
    orems
    0.43
    *
    0.43
     reminders
    0.43
    ↵↵
    0.41
    m
    0.40
    ची
    0.40
    いても
    0.40
     lâm
    0.40
    POSITIVE LOGITS
     attho
    0.53
    participation
    0.52
    yoga
    0.50
     大学
    0.50
     contesto
    0.49
     університету
    0.49
     መድ
    0.49
    accountId
    0.49
     सदस्यता
    0.49
    ̔
    0.47
    Activations Density 0.000%

    No Known Activations