Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 17682
    Prev
    Next
    INDEX
    Explanations

    elo rating system

    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_16_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
     Received
    0.50
    н
    0.47
    Received
    0.46
     받
    0.45
     receive
    0.45
     recieved
    0.45
     Receive
    0.45
    CEEDINGS
    0.45
     received
    0.45
     boiled
    0.45
    POSITIVE LOGITS
    risque
    0.54
    ق
    0.52
    crit
    0.47
    riff
    0.46
    uacute
    0.45
    kipun
    0.45
    iração
    0.43
    女の子
    0.43
    dd
    0.42
    erté
    0.42
    Activations Density 0.000%

    No Known Activations