© 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. 109584
    Prev
    Next
    INDEX
    Explanations

    news articles and technical descriptions

    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
    god
    0.50
     god
    0.46
     cof
    0.41
    God
    0.41
     gods
    0.38
    神
    0.38
     God
    0.37
    Explore
    0.37
    rema
    0.36
     Gods
    0.35
    POSITIVE LOGITS
     Beetle
    0.40
     isot
    0.38
     finish
    0.38
    种类
    0.38
    侃
    0.38
    榭
    0.38
     erreur
    0.37
    AvlTree
    0.37
    ڈن
    0.37
    ഗി
    0.36
    Activations Density 0.000%

    No Known Activations