© 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-65K
    7. 20538
    Prev
    Next
    INDEX
    Explanations

    phrases starting with `and` or `based on`

    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_65k_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
     സമൂ
    0.56
    tFileInputExcel
    0.54
    posta
    0.51
     pédicule
    0.50
    parvec
    0.50
    MDEwOlJlcG
    0.48
    輒
    0.47
    modelLogin
    0.47
    odi
    0.46
    ⺊
    0.46
    POSITIVE LOGITS
    ↵↵
    0.59
     intentos
    0.47
     noche
    0.45
     honors
    0.44
     with
    0.43
     Krieg
    0.43
    sandwich
    0.40
    copies
    0.40
    ↵↵↵
    0.40
     fulfill
    0.40
    Activations Density 0.006%

    No Known Activations