© 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-65K
    7. 49416
    Prev
    Next
    INDEX
    Explanations

    amber and ember

    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_65k_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
     titan
    0.43
     Titan
    0.43
     Brazil
    0.42
    ~\
    0.41
    VA
    0.40
     marshmallow
    0.40
     balloon
    0.38
    Brazil
    0.38
     Nvidia
    0.38
    TN
    0.38
    POSITIVE LOGITS
     sobbing
    0.41
     फ़र
    0.41
     নীচে
    0.41
     shortening
    0.41
    リュー
    0.41
     школова
    0.40
    ставля
    0.38
    leyin
    0.38
    丟
    0.38
     provoked
    0.38
    Activations Density 0.008%

    No Known Activations