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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 6856
    Prev
    Next
    INDEX
    Explanations

    places, entities, or groups

    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_16_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
     တော့
    0.50
     忄
    0.48
    <unused711>
    0.47
     වෙන
    0.46
     vielfält
    0.46
     друго
    0.45
    <unused1908>
    0.45
    󰡕
    0.45
    <unused510>
    0.45
    myButtons
    0.44
    POSITIVE LOGITS
    f
    0.62
    5
    0.58
    F
    0.55
    E
    0.53
    2
    0.49
    ال
    0.46
    O
    0.46
    S
    0.46
    8
    0.46
    0.45
    Activations Density 0.184%

    No Known Activations