© 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-65K
    7. 11735
    Prev
    Next
    INDEX
    Explanations

    field of, field adjusted, fieldcraft, objectives

    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_65k_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
    et
    0.85
     hùng
    0.75
    고
    0.74
    on
    0.69
     evils
    0.69
    ne
    0.67
    p
    0.66
    ле
    0.66
    ко
    0.65
    на
    0.64
    POSITIVE LOGITS
     field
    1.46
     Field
    1.38
    Field
    1.37
     campo
    1.13
     FIELD
    1.09
     lapangan
    1.02
    フィールド
    0.99
     फील्ड
    0.96
     fields
    0.96
     fielding
    0.96
    Activations Density 0.029%

    No Known Activations