© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201022
    Prev
    Next
    INDEX
    Explanations

    excessive desire or craving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    on
    0.53
    '
    0.46
     Sugar
    0.45
     Shawn
    0.45
    ial
    0.45
    eries
    0.44
    Shawn
    0.44
    é
    0.43
    ğ
    0.42
    떤
    0.42
    POSITIVE LOGITS
     admiss
    0.46
     ridurre
    0.45
     ahorro
    0.44
     discos
    0.44
     interessant
    0.43
     күзгү
    0.43
     accessori
    0.43
    慳
    0.43
     naturali
    0.42
    𝓾
    0.42
    Activations Density 0.004%

    No Known Activations