© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10104
    Prev
    Next
    INDEX
    Explanations

    Probability, hours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (|
    0.39
     hém
    0.37
    motionProxy
    0.36
     runat
    0.36
    といった
    0.35
    。(
    0.35
     '.';
    0.35
    YE
    0.33
    ('/').
    0.33
    츠
    0.33
    POSITIVE LOGITS
     उल्लेखनीय
    0.39
    ちなみに
    0.37
     देखें
    0.36
     علیحد
    0.35
     العديد
    0.35
     सहभागी
    0.34
     निकली
    0.34
     Сейчас
    0.34
    PS
    0.33
    疯狂
    0.33
    Activations Density 0.078%

    No Known Activations