© 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. 36946
    Prev
    Next
    INDEX
    Explanations

    someone determined

    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
     viya
    0.54
    ROTTLE
    0.48
     था
    0.48
    inicio
    0.43
    Zv
    0.42
    ᱖
    0.41
     ছিল
    0.40
     repulsive
    0.40
     可愛い
    0.40
     TNI
    0.40
    POSITIVE LOGITS
    ెండు
    0.46
    chsel
    0.45
    ट्टे
    0.45
    Business
    0.43
    Allen
    0.43
    钲
    0.42
    Jon
    0.42
    CenterX
    0.42
    ablen
    0.42
    Businesses
    0.42
    Activations Density 0.020%

    No Known Activations