© 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. 35808
    Prev
    Next
    INDEX
    Explanations

    printing process

    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
    拈
    0.48
     गठित
    0.47
    𒉿
    0.46
    ाराम
    0.45
    ే
    0.45
     रखने
    0.44
    ؓ
    0.44
    𝐫
    0.44
     करने
    0.44
     ব্যবস্থ
    0.44
    POSITIVE LOGITS
    6
    0.55
    db
    0.53
    DB
    0.52
    use
    0.51
    JSON
    0.50
     on
    0.49
    dw
    0.49
    abu
    0.48
    debug
    0.48
    inside
    0.48
    Activations Density 0.005%

    No Known Activations