© 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. 8683
    Prev
    Next
    INDEX
    Explanations

    numerical precision

    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
    梦
    0.50
     Nickelodeon
    0.48
     పూ
    0.48
     CONNE
    0.45
     Passe
    0.45
    貓
    0.45
     ड्राई
    0.44
     Invite
    0.43
     Eligibility
    0.42
    夢
    0.41
    POSITIVE LOGITS
     decimal
    1.06
     BigDecimal
    1.05
    BigDecimal
    1.02
    Decimal
    0.95
    Big
    0.93
     bigint
    0.93
     precision
    0.91
     Decimal
    0.91
    decimal
    0.90
     Big
    0.89
    Activations Density 0.036%

    No Known Activations