© 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. 16-GEMMASCOPE-2-RES-262K
    7. 1315
    Prev
    Next
    INDEX
    Explanations

    finance expert, department, guru

    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_16_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
    étrique
    1.01
     is
    0.98
    是
    0.96
    ెంట్
    0.95
    دى
    0.89
    spanning
    0.88
    diendo
    0.88
    కు
    0.87
    ας
    0.85
    số
    0.85
    POSITIVE LOGITS
     a
    1.43
     Finance
    1.34
     finance
    1.25
    it
    1.20
    il
    1.15
    id
    1.15
     be
    1.15
     Y
    1.15
     M
    1.14
     n
    1.13
    Activations Density 0.005%

    No Known Activations