© 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. 50912
    Prev
    Next
    INDEX
    Explanations

    football, Solana, history

    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
     Atr
    0.48
    月
    0.46
    ل
    0.45
    ન
    0.45
    í
    0.45
    2
    0.45
    （
    0.45
    \
    0.44
    সং
    0.44
     attitudes
    0.44
    POSITIVE LOGITS
    cake
    0.49
    whel
    0.48
    rahydro
    0.47
    ູບ
    0.45
    ณา
    0.45
     hại
    0.45
     herni
    0.45
    ুরি
    0.44
    贝尔
    0.44
     کنیم
    0.43
    Activations Density 0.003%

    No Known Activations