© 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. 16800
    Prev
    Next
    INDEX
    Explanations

    making everyday

    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
    ila
    0.50
    uma
    0.46
    -
    0.45
    ola
    0.44
     yoki
    0.44
    ampak
    0.44
    udi
    0.43
    enda
    0.42
     என்ற
    0.42
     alebo
    0.42
    POSITIVE LOGITS
    💩
    0.46
    シーズン
    0.46
     όλ
    0.45
     sediment
    0.44
    気温
    0.43
    ⇅
    0.43
     fertilized
    0.41
     it
    0.41
     atmos
    0.41
    ๚
    0.41
    Activations Density 0.001%

    No Known Activations