© 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. 40-GEMMASCOPE-2-RES-262K
    7. 10859
    Prev
    Next
    INDEX
    Explanations

    enter into

    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_40_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
    '
    0.46
    ک
    0.45
    ก
    0.40
    ลง
    0.39
    คะ
    0.39
     للخ
    0.39
    ളി
    0.38
    א
    0.38
     reveal
    0.37
    ILING
    0.37
    POSITIVE LOGITS
     into
    0.79
     vào
    0.73
    into
    0.71
     entered
    0.70
    Into
    0.68
    entered
    0.67
    taining
    0.65
    Entered
    0.63
     Entered
    0.63
     entering
    0.62
    Activations Density 0.013%

    No Known Activations