© 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. 31-GEMMASCOPE-2-RES-65K
    7. 15993
    Prev
    Next
    INDEX
    Explanations

    car, unlimited travel

    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_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
    ய்
    0.57
     messageFields
    0.49
     firme
    0.48
    ीट
    0.48
    bicara
    0.47
    ğ
    0.47
    ాన్
    0.46
     Congrès
    0.46
     вый
    0.46
     प्रशंसा
    0.46
    POSITIVE LOGITS
    EN
    0.55
    ，
    0.47
    u
    0.44
    eller
    0.43
    INA
    0.42
    ENT
    0.42
    ts
    0.41
    itsch
    0.41
    0.41
    安全
    0.41
    Activations Density 0.003%

    No Known Activations