© 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. 40-GEMMASCOPE-2-RES-262K
    7. 224280
    Prev
    Next
    INDEX
    Explanations

    great and grand phrases

    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
    袭
    0.44
    壹百
    0.43
    伍章
    0.40
    ₂,
    0.40
    قيقي
    0.40
    ISAM
    0.39
    oldsymbol
    0.39
    იმ
    0.39
     [\
    0.38
    ﹝
    0.38
    POSITIVE LOGITS
     cities
    0.51
     πέ
    0.42
     piles
    0.41
     dark
    0.40
     gatherings
    0.39
     countries
    0.38
     surgical
    0.38
     aggreg
    0.37
    cities
    0.37
     संग्रहालय
    0.37
    Activations Density 0.005%

    No Known Activations