© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46989
    Prev
    Next
    INDEX
    Explanations

    draw attention

    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
    า
    0.50
     ಲೋ
    0.50
     церков
    0.50
     четыре
    0.48
     вакци
    0.47
    itabbo
    0.47
     следующим
    0.46
    ーン
    0.46
    olisian
    0.46
    इस
    0.46
    POSITIVE LOGITS
    ,
    0.49
     attract
    0.45
     extensive
    0.43
     Baja
    0.42
     neuer
    0.41
     underground
    0.40
    Jpa
    0.40
     attractive
    0.39
     superb
    0.39
     L
    0.39
    Activations Density 0.019%

    No Known Activations