© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 32806
    Prev
    Next
    INDEX
    Explanations

    Crisis, day, recruitment, Spot

    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_40_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
     smelled
    0.44
     smells
    0.44
     graças
    0.42
     smell
    0.42
    CHK
    0.41
     scent
    0.40
     unica
    0.40
    蚬
    0.39
     gracias
    0.39
     mexican
    0.39
    POSITIVE LOGITS
    Nor
    0.40
    indoor
    0.39
    ത്
    0.39
    emotional
    0.38
    尋
    0.37
    തു
    0.35
    メイド
    0.35
     உறுதி
    0.35
    Billboard
    0.35
    部品
    0.35
    Activations Density 0.000%

    No Known Activations