© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8103
    Prev
    Next
    INDEX
    Explanations

    lists of text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    こちらは
    1.55
    nych
    1.44
     बार
    1.35
    )`,
    1.35
     פ
    1.31
     από
    1.31
    một
    1.30
    s
    1.25
    larında
    1.24
    lında
    1.23
    POSITIVE LOGITS
    ти
    1.93
    но
    1.75
    ine
    1.52
    effectiveness
    1.51
    اد
    1.48
    ৯
    1.47
    ى
    1.45
    ಾ
    1.38
    ని
    1.37
    おります
    1.37
    Activations Density 0.257%

    No Known Activations