© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40893
    Prev
    Next
    INDEX
    Explanations

    built on, tied to, using

    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_31_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
     چک
    0.44
     бен
    0.43
     Sardar
    0.43
    కు
    0.41
    FromJson
    0.41
    湖
    0.40
    arzt
    0.39
     khấu
    0.39
    ப்பு
    0.39
    MktCap
    0.39
    POSITIVE LOGITS
     adaptability
    0.47
    8
    0.47
     mornings
    0.46
     어린이
    0.46
    ton
    0.43
     mismatch
    0.43
     symb
    0.43
     robustness
    0.42
    𝚐
    0.42
     систе
    0.42
    Activations Density 0.000%

    No Known Activations