© 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-262K
    7. 125927
    Prev
    Next
    INDEX
    Explanations

    bill amount, weights, KEY

    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_262k_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
     উঠলাম
    0.44
    MouseMove
    0.44
     createCanvas
    0.41
    َّة
    0.41
     他
    0.41
    㙋
    0.41
     نحاول
    0.40
    하거나
    0.40
     poner
    0.39
     Erklärung
    0.39
    POSITIVE LOGITS
    анд
    0.46
     are
    0.44
    از
    0.44
    ال
    0.44
    ຂອງ
    0.42
    are
    0.42
     sacram
    0.42
    ف
    0.42
    of
    0.41
     miserable
    0.41
    Activations Density 0.006%

    No Known Activations