© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 205229
    Prev
    Next
    INDEX
    Explanations

    downward flow direction

    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
     Western
    0.46
    Western
    0.41
    setBadge
    0.40
     পশ্চিমা
    0.39
    钯
    0.39
    Rim
    0.38
    西方
    0.38
    َرْ
    0.37
    呎
    0.37
     Westen
    0.37
    POSITIVE LOGITS
    ↓
    1.23
     ↓
    1.12
     down
    1.01
    downarrow
    1.01
     downwards
    1.01
     downward
    1.00
    ⬇
    0.97
     вниз
    0.95
     Down
    0.92
    down
    0.91
    Activations Density 0.009%

    No Known Activations