© 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. 2160
    Prev
    Next
    INDEX
    Explanations

    business documents and processes

    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
    influence
    0.37
    magnitude
    0.36
     plasticity
    0.36
    horizontal
    0.36
    variety
    0.36
     causative
    0.36
    importance
    0.35
    }^{-}
    0.35
    example
    0.34
     გამოყენ
    0.34
    POSITIVE LOGITS
     payments
    0.57
     invoices
    0.55
     requests
    0.54
     financials
    0.50
     invoice
    0.47
     Invoice
    0.47
     paperwork
    0.46
     Certificates
    0.46
     questionnaires
    0.45
     bookings
    0.45
    Activations Density 0.111%

    No Known Activations