© 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. 31-GEMMASCOPE-2-RES-262K
    7. 113047
    Prev
    Next
    INDEX
    Explanations

    medical receipts summary

    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
    Chen
    0.53
    ه
    0.50
    a
    0.49
    د
    0.49
    en
    0.47
    En
    0.46
    Murder
    0.46
    Decrypt
    0.46
    م
    0.46
    ilet
    0.45
    POSITIVE LOGITS
     line
    0.54
     predominant
    0.51
     computation
    0.50
     blossom
    0.50
     discrepancy
    0.49
     entice
    0.49
     impedance
    0.48
     anomaly
    0.47
     overarching
    0.47
     numerical
    0.47
    Activations Density 0.000%

    No Known Activations