© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 98744
    Prev
    Next
    INDEX
    Explanations

    siblings, children, and parents

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers, ages, and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    करने
    0.44
    稒
    0.41
    ప్ప
    0.41
    ;-
    0.41
    ,&
    0.41
    antiene
    0.40
     veoma
    0.40
    发表
    0.39
    ,@
    0.39
    excerpt
    0.39
    POSITIVE LOGITS
     Júnior
    0.52
     দিয়েছিলেন
    0.49
     Maje
    0.46
     জানিয়েছিলেন
    0.46
    éon
    0.45
    ichting
    0.44
     দেখেছিলেন
    0.42
     বাচ্চ
    0.41
     Joaquín
    0.41
    ḥ
    0.40
    Activations Density 0.000%

    No Known Activations