© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 15856
    Prev
    Next
    INDEX
    Explanations

    adding and combining fractions

    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_40_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
    ज्य
    0.42
     нәрсә
    0.41
     Biswas
    0.41
     ദ
    0.40
     एक्सिस
    0.40
     cupboards
    0.38
    wikipedia
    0.38
    痞
    0.38
     रहस्य
    0.38
     पाचन
    0.38
    POSITIVE LOGITS
    合并
    0.52
    合併
    0.52
     amalgam
    0.45
     fluxes
    0.44
     numerator
    0.44
     merger
    0.42
     merged
    0.42
     merge
    0.42
    Now
    0.41
    merged
    0.40
    Activations Density 0.002%

    No Known Activations