© 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. 32461
    Prev
    Next
    INDEX
    Explanations

    unique items, before then, material

    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
     texture
    0.51
     excised
    0.50
    لد
    0.48
     authToken
    0.47
    Texture
    0.46
    acuation
    0.46
    Cooldown
    0.46
    ג
    0.46
    г
    0.46
    二氧化
    0.45
    POSITIVE LOGITS
     Dom
    0.51
     Murdoch
    0.49
     Ladies
    0.46
     Lab
    0.45
     Cambridge
    0.45
    Dom
    0.44
     Sav
    0.44
     Rupert
    0.44
     Aire
    0.44
     Arthur
    0.43
    Activations Density 0.001%

    No Known Activations