© 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. 30680
    Prev
    Next
    INDEX
    Explanations

    document beginnings and titles

    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
    也可以
    0.46
     বিষয়ক
    0.43
     Pow
    0.41
    leaf
    0.39
     નો
    0.39
    ')";
    0.38
     मिळणार
    0.38
     వే
    0.38
    চিব
    0.38
     ఆహ
    0.38
    POSITIVE LOGITS
    š
    0.39
    Title
    0.37
     crossing
    0.37
    Ö
    0.35
     Heaven
    0.35
     ذلك
    0.35
     forcible
    0.35
    Jag
    0.34
     shortly
    0.34
    Crossing
    0.34
    Activations Density 0.003%

    No Known Activations