© 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. 15735
    Prev
    Next
    INDEX
    Explanations

    youtube links

    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
    -
    0.64
     (
    0.63
    or
    0.61
    *
    0.57
     to
    0.56
     '
    0.55
    /
    0.52
     ‘
    0.52
    @
    0.51
    a
    0.50
    POSITIVE LOGITS
     rapidity
    0.63
     championnat
    0.55
     gyors
    0.54
     glLightfv
    0.53
    TaskPojo
    0.52
     ovipares
    0.52
     剤
    0.52
    EnglishMarks
    0.51
     keempat
    0.50
     سرعت
    0.50
    Activations Density 0.008%

    No Known Activations