© 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. 40-GEMMASCOPE-2-RES-262K
    4. 109569
    Prev
    Next
    INDEX
    Explanations

    origins and their connections

    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
     efficacement
    0.39
    明け
    0.38
    𝘶
    0.38
     gages
    0.36
    罡
    0.35
    襷
    0.35
    𓏸
    0.35
     fé
    0.34
     rooster
    0.34
     ஆகவே
    0.34
    POSITIVE LOGITS
    larla
    0.41
    ğından
    0.40
    oding
    0.40
    BITMAP
    0.40
    RECEIVED
    0.40
    receive
    0.39
     কোথ
    0.38
     receive
    0.38
     recieve
    0.37
     SIG
    0.37
    Activations Density 0.002%

    No Known Activations