© 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. 174227
    Prev
    Next
    INDEX
    Explanations

    Green Gym, public monitor, such comments

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

    description of access or history

    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
    ǎng
    0.54
    ЛА
    0.51
    мера
    0.49
    ראה
    0.47
    遼
    0.46
    ᾰ
    0.46
    拉克
    0.46
     án
    0.45
    ПР
    0.45
    ങ്ക
    0.45
    POSITIVE LOGITS
     તેનું
    0.45
     فإن
    0.43
     पीड़ित
    0.42
     آسان
    0.42
    anomaly
    0.42
     abnorm
    0.41
     প্রমাণিত
    0.41
     monotonic
    0.40
     ندارد
    0.40
    EndY
    0.39
    Activations Density 0.001%

    No Known Activations