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. 27858
    Prev
    Next
    INDEX
    Explanations

    speech, text, sentences, arguments

    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
    D
    0.36
    W
    0.36
    <0x0D>
    0.32
     ousted
    0.32
     విద్య
    0.30
     అ
    0.29
     הד
    0.29
     a
    0.29
     прове
    0.28
    alers
    0.28
    POSITIVE LOGITS
    кс
    0.39
    ンの
    0.38
    ے
    0.37
     här
    0.35
    лық
    0.35
    с
    0.34
    к
    0.34
     respectivos
    0.33
    шения
    0.33
    ﺲ
    0.32
    Activations Density 0.102%

    No Known Activations