© 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-3-270M-IT
    3. 15-GEMMASCOPE-2-RES-262K
    4. 69596
    Prev
    Next
    INDEX
    Explanations

    code blocks (`Sub`, `function`, `document`, `div`, `<`)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
     chapitre
    1.01
    钛
    0.90
    oba
    0.83
    Mental
    0.82
     словарь
    0.75
     ainsi
    0.74
     Petersburg
    0.72
    Mode
    0.71
    Kunst
    0.70
     führ
    0.70
    POSITIVE LOGITS
     actually
    1.95
    жда
    1.88
     <
    1.87
     rescu
    1.87
     querido
    1.86
     Cheek
    1.82
     كده
    1.80
    落在
    1.79
    ukkig
    1.78
     pylori
    1.75
    Activations Density 0.013%

    No Known Activations