© 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. 187902
    Prev
    Next
    INDEX
    Explanations

    fortress, salvation, affliction

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

    foreign language words

    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
     nilpotent
    0.43
     stipulated
    0.42
     disparity
    0.41
     dispersal
    0.41
     selatan
    0.40
    启动
    0.40
     ？
    0.40
    ወስ
    0.39
     sodium
    0.39
     mythological
    0.39
    POSITIVE LOGITS
    の両
    0.57
    ья
    0.52
     её
    0.50
    ்கு
    0.48
    漸
    0.47
     всех
    0.46
     всей
    0.46
    бора
    0.45
    ё
    0.45
     более
    0.45
    Activations Density 0.001%

    No Known Activations