© 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. 15685
    Prev
    Next
    INDEX
    Explanations

    waiver request

    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
     Ethan
    0.46
     Съ
    0.46
     speculators
    0.46
     Omnibus
    0.45
    綑
    0.45
    థ
    0.44
     Stray
    0.44
     Absolutely
    0.44
     ကျွန်
    0.44
     банк
    0.43
    POSITIVE LOGITS
    Data
    0.42
    mo
    0.41
    {{
    0.41
    لمه
    0.41
    cro
    0.40
    File
    0.39
    Activity
    0.38
     activity
    0.38
     शिकायत
    0.38
    ${\
    0.38
    Activations Density 0.003%

    No Known Activations