© 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. 50709
    Prev
    Next
    INDEX
    Explanations

    classification and weights

    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
     क्यूट
    0.47
    ضغط
    0.46
    可爱
    0.46
    zę
    0.45
    yszer
    0.45
    Привет
    0.43
    ándolo
    0.43
    蔼
    0.43
    jegyz
    0.42
    स्‍या
    0.42
    POSITIVE LOGITS
     مشینوں
    0.50
     multin
    0.47
     upland
    0.47
     بتوان
    0.45
     المست
    0.44
     ज
    0.44
     موض
    0.44
     grasslands
    0.44
     socio
    0.44
     gio
    0.43
    Activations Density 0.001%

    No Known Activations