© 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. 6066
    Prev
    Next
    INDEX
    Explanations

    words relating to specific entities

    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
    เก่า
    0.44
    iscale
    0.42
    ぃ
    0.40
    forcements
    0.40
    われ
    0.39
     discontinuity
    0.39
    Ah
    0.38
    nn
    0.38
     ሥራ
    0.38
    는
    0.38
    POSITIVE LOGITS
     velmi
    0.48
     ખૂબ
    0.48
     hyvin
    0.47
     коюмдары
    0.46
     yür
    0.46
     güçlü
    0.46
     wyjątk
    0.46
     excepc
    0.45
     své
    0.43
     sportsmen
    0.43
    Activations Density 0.000%

    No Known Activations