© 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. 12850
    Prev
    Next
    INDEX
    Explanations

    water state transitions and properties

    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
    财政
    0.83
     финансо
    0.81
    权力
    0.80
     паліты
    0.75
    运营
    0.75
    谋
    0.75
    监管
    0.74
    绩效
    0.73
     yatırım
    0.72
    谴
    0.72
    POSITIVE LOGITS
     water
    1.40
     liquid
    1.32
     viscosity
    1.20
     liquids
    1.20
    water
    1.17
     fluids
    1.16
     fluid
    1.15
    liquid
    1.14
     aqueous
    1.07
     Water
    1.05
    Activations Density 0.168%

    No Known Activations