© 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. 143627
    Prev
    Next
    INDEX
    Explanations

    xml declarations and namespaces

    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
     ιστο
    0.46
     kia
    0.41
     Structure
    0.40
     структуру
    0.40
     sayf
    0.40
     истории
    0.40
     Ε
    0.39
     સમય
    0.39
     จำ
    0.39
    <0x99>
    0.38
    POSITIVE LOGITS
    kata
    0.50
    hanga
    0.46
    Introducing
    0.43
    codigo
    0.43
     zaradi
    0.42
    obranch
    0.42
     nombr
    0.40
     zbog
    0.40
    ذهب
    0.39
    ্তা
    0.39
    Activations Density 0.000%

    No Known Activations