© 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. 43566
    Prev
    Next
    INDEX
    Explanations

    extra fee

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

    stretching and forcing

    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
    ModelGrid
    0.56
    PlainText
    0.52
     контроля
    0.51
    이랑
    0.50
    ષ
    0.49
     Rowe
    0.49
    𝚙
    0.49
     контроль
    0.48
     Browning
    0.47
    града
    0.47
    POSITIVE LOGITS
    汽車
    0.43
    投
    0.43
    ตู
    0.41
     المن
    0.39
     المح
    0.39
    apa
    0.38
     z
    0.38
     mě
    0.38
     mistaken
    0.38
    هرة
    0.38
    Activations Density 0.000%

    No Known Activations