© 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. 40624
    Prev
    Next
    INDEX
    Explanations

    wedding rings

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

    go to, join, went extinct

    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
    ¯
    0.48
    tid
    0.47
     वंश
    0.47
    ısı
    0.46
     µ
    0.46
     pah
    0.45
     लगभग
    0.45
     palju
    0.45
    ठी
    0.45
    pli
    0.44
    POSITIVE LOGITS
    ز
    0.53
    ア
    0.52
     agendas
    0.46
     aspetto
    0.45
    拯
    0.45
    病的
    0.44
     kindred
    0.44
    ル
    0.44
     disciplines
    0.44
    beitet
    0.44
    Activations Density 0.000%

    No Known Activations