© 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. 27728
    Prev
    Next
    INDEX
    Explanations

    sale by Private Treaty

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

    talk about, type in

    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
    사용
    0.47
    gunakan
    0.43
    ü
    0.42
    ta
    0.42
    úč
    0.42
    ユーザ
    0.42
    未使用
    0.41
    user
    0.41
    用户
    0.40
    ı
    0.40
    POSITIVE LOGITS
     newMovie
    0.50
     Scr
    0.49
     recomiendo
    0.47
     ingl
    0.46
     intertw
    0.45
    ხვევ
    0.45
     fizemos
    0.45
     infil
    0.45
     recomendamos
    0.45
     lollipop
    0.44
    Activations Density 0.000%

    No Known Activations