© 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. 29172
    Prev
    Next
    INDEX
    Explanations

    Here's a breakdown

    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
    ب
    0.48
    ব
    0.44
    ယ
    0.44
    里昂
    0.43
    އ
    0.43
    ام
    0.43
    ต
    0.43
     envisaged
    0.40
    কে
    0.40
    င်
    0.40
    POSITIVE LOGITS
     असताना
    0.57
    --->
    0.52
    ➡
    0.51
     బె
    0.50
     Power
    0.48
    islang
    0.48
    akespe
    0.46
     Korn
    0.46
    twice
    0.46
    ҝ
    0.46
    Activations Density 0.000%

    No Known Activations