© 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. 127862
    Prev
    Next
    INDEX
    Explanations

    question about, transition or, step of

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

    title, pain, duration

    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
     स्टाइल
    0.53
     बादशाह
    0.51
     เรียน
    0.50
     谢
    0.50
     вигляді
    0.50
    𒈠
    0.50
     韩
    0.49
     naszych
    0.49
     点击
    0.48
    丳
    0.48
    POSITIVE LOGITS
    os
    0.60
    as
    0.55
    3
    0.48
    a
    0.48
    A
    0.47
    *
    0.46
    ing
    0.46
    O
    0.45
    ein
    0.43
     proxies
    0.43
    Activations Density 0.001%

    No Known Activations