© 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. 216520
    Prev
    Next
    INDEX
    Explanations

    fearing for, here are, case will

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

    inherently, generally, repair, slot, import

    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
    アイス
    0.49
    ニ
    0.47
    余裕
    0.45
    δ
    0.45
    画像
    0.45
    ヘ
    0.45
    ポ
    0.45
    ヒ
    0.44
    מ
    0.44
    オリ
    0.43
    POSITIVE LOGITS
     ngừa
    0.45
    使用的是
    0.42
     tokenId
    0.41
    ख्या
    0.40
     nulla
    0.40
     Sunday
    0.40
     sandy
    0.40
     paddock
    0.40
     trivia
    0.40
     switcher
    0.40
    Activations Density 0.001%

    No Known Activations