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. 14352
    Prev
    Next
    INDEX
    Explanations

    given that

    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
     sẽ
    0.47
     calculate
    0.46
    <unused530>
    0.46
     определяет
    0.44
     হলেই
    0.44
    就會
    0.44
     determine
    0.43
     če
    0.43
     calcule
    0.43
     Ero
    0.43
    POSITIVE LOGITS
     اینکه
    0.46
    atum
    0.43
    ha
    0.43
    सम्म
    0.41
    t
    0.41
    疫情
    0.40
    et
    0.40
    ma
    0.40
    তা
    0.40
    andi
    0.39
    Activations Density 0.006%

    No Known Activations