© 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. 51677
    Prev
    Next
    INDEX
    Explanations

    right-click actions or details

    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
    隠
    0.39
    tod
    0.38
     dört
    0.38
     fornecer
    0.38
    urro
    0.37
    JO
    0.37
     Todas
    0.37
    buckets
    0.37
     véritables
    0.37
     inheritance
    0.37
    POSITIVE LOGITS
    鈍
    0.45
     unsatisfactory
    0.43
     원하는
    0.42
     유리
    0.39
     desired
    0.39
     gewüns
    0.37
    VersionUID
    0.37
     интересу
    0.37
     arr
    0.36
    想要
    0.36
    Activations Density 0.098%

    No Known Activations