© 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. 56925
    Prev
    Next
    INDEX
    Explanations

    analyzing options and statements

    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
    楨
    0.46
     bhavanti
    0.45
    ၷ
    0.44
    บุรี
    0.43
    ρή
    0.42
    εια
    0.42
    ण्या
    0.42
     লাগিল
    0.41
     rallying
    0.41
     नाम
    0.40
    POSITIVE LOGITS
    d
    0.53
    imed
    0.45
     صاف
    0.45
    r
    0.45
    rpt
    0.44
    herent
    0.44
     anter
    0.44
     Mascul
    0.43
    ged
    0.43
    herence
    0.42
    Activations Density 0.002%

    No Known Activations