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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 85236
    Prev
    Next
    INDEX
    Explanations

    specificity and detail

    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
    irdik
    0.49
     சந்தேக
    0.45
     LOST
    0.45
    羊
    0.45
    icillium
    0.43
     voiture
    0.41
     ယ
    0.41
    nurse
    0.40
     consequências
    0.40
     verloren
    0.40
    POSITIVE LOGITS
     परि
    0.44
     vei
    0.42
    ف
    0.42
     देखिए
    0.41
     સમા
    0.41
     Xác
    0.40
    тся
    0.40
     સહ
    0.40
     ввод
    0.40
    лыгы
    0.40
    Activations Density 0.000%

    No Known Activations