© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 191340
    Prev
    Next
    INDEX
    Explanations

    Castle, Quaternion, mouse, foundations visible

    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_40_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
    琳
    0.38
    ▄
    0.38
     ऑडियो
    0.37
    weds
    0.37
    Coastal
    0.37
    ĺ
    0.36
     وسهلا
    0.36
    sect
    0.36
    ::::
    0.35
    neau
    0.35
    POSITIVE LOGITS
     classific
    0.41
     Spare
    0.40
    ofar
    0.39
     therefrom
    0.39
    糁
    0.38
     LPA
    0.37
     army
    0.37
     classifiers
    0.37
     পাঞ্জ
    0.37
     пуль
    0.37
    Activations Density 0.002%

    No Known Activations