© 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-65K
    7. 30714
    Prev
    Next
    INDEX
    Explanations

    car or meter

    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
     Chúa
    0.46
    ங்களை
    0.44
     Unicode
    0.44
     Му
    0.44
     Māori
    0.43
    У
    0.42
    То
    0.42
     Maia
    0.42
    Мо
    0.41
     subjunctive
    0.41
    POSITIVE LOGITS
    科技
    0.42
    මින්
    0.41
     xaxis
    0.41
     বাজেট
    0.40
    텟
    0.40
     obsahuje
    0.40
    เคร
    0.39
    স্পতিবার
    0.38
     fileSize
    0.38
     impacto
    0.38
    Activations Density 0.036%

    No Known Activations