© 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. 40-GEMMASCOPE-2-RES-65K
    7. 49130
    Prev
    Next
    INDEX
    Explanations

    What is or programming

    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_40_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
    ᑉ
    0.41
    abut
    0.37
    Printer
    0.35
     осигура
    0.35
     Booklet
    0.35
    ettre
    0.34
     Zeitschr
    0.34
    word
    0.34
     advices
    0.34
    蠢
    0.34
    POSITIVE LOGITS
     haunt
    0.43
    ನೇ
    0.40
     funk
    0.39
    ocity
    0.39
     والإ
    0.39
     arba
    0.39
     अफ्री
    0.38
     African
    0.37
    ਾਨ
    0.37
     ವಿಶೇಷ
    0.37
    Activations Density 0.001%

    No Known Activations