© 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. 77656
    Prev
    Next
    INDEX
    Explanations

    is responsible

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

    urine, Koreans, enable, together, trials, sadness, page

    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
    ศาสตร์
    0.47
    нти
    0.46
    ле
    0.46
    гда
    0.46
    рети
    0.45
     थीटा
    0.45
    θ
    0.45
    κο
    0.45
    довж
    0.45
     Σε
    0.44
    POSITIVE LOGITS
     lainnya
    0.47
     Bhav
    0.44
     गौर
    0.44
     bbs
    0.42
    礼物
    0.42
     Adin
    0.42
     Misalnya
    0.42
    otea
    0.41
     समर्थ
    0.41
     نہیں۔
    0.41
    Activations Density 0.000%

    No Known Activations