© 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. 123785
    Prev
    Next
    INDEX
    Explanations

    speed and steps towards

    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
    لت
    0.49
    cherche
    0.48
     Feuerwehr
    0.47
    ور
    0.46
    став
    0.46
    존
    0.46
    criptive
    0.46
    czne
    0.45
    spirational
    0.45
    ז
    0.45
    POSITIVE LOGITS
     buyers
    0.47
     history
    0.46
     dugo
    0.45
     Russia
    0.45
     buyer
    0.45
     blows
    0.44
     hired
    0.44
     huo
    0.44
     urea
    0.43
     però
    0.43
    Activations Density 0.004%

    No Known Activations