Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 401
    Prev
    Next
    INDEX
    Explanations

    search for strings or terms

    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
    pouring
    0.43
    rául
    0.42
    тан
    0.40
    getSaveLocation
    0.40
    Choosing
    0.39
    ฐ
    0.39
    ikovsky
    0.39
    蒴
    0.39
    Besch
    0.39
    AccessException
    0.38
    POSITIVE LOGITS
     search
    1.28
     matching
    1.24
     searches
    1.19
     searched
    1.17
    匹配
    1.17
     match
    1.15
     searching
    1.14
     matches
    1.13
     tìm
    1.11
    search
    1.09
    Activations Density 0.099%

    No Known Activations