© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77789
    Prev
    Next
    INDEX
    Explanations

    Mom Ever, search query

    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
    ز
    0.47
     brushing
    0.47
     زائ
    0.46
    दरअसल
    0.43
    ்து
    0.43
    醣
    0.43
    zunehmen
    0.42
     nomenclature
    0.42
    াহরণ
    0.41
    סטי
    0.41
    POSITIVE LOGITS
    вной
    0.47
     प्रतिबिंब
    0.45
     देशी
    0.45
     ولكن
    0.44
     дом
    0.44
    Answer
    0.42
    したら
    0.42
    /*
    0.42
     אבל
    0.41
     घरा
    0.41
    Activations Density 0.001%

    No Known Activations