© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 21028
    Prev
    Next
    INDEX
    Explanations

    the case or status

    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
     {
    0.53
     recognition
    0.50
     tragedy
    0.49
     ->
    0.48
     Colonel
    0.48
     trium
    0.44
     idx
    0.44
     typed
    0.43
     dre
    0.43
     risk
    0.43
    POSITIVE LOGITS
    겠지만
    0.50
    ᐸ
    0.46
    OPTV
    0.45
    𝘱
    0.44
    tiempo
    0.44
     খাত
    0.44
    𝕡
    0.44
    𝘦
    0.43
     subTest
    0.43
    profiss
    0.43
    Activations Density 0.001%

    No Known Activations