Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 2554
    Prev
    Next
    INDEX
    Explanations

    Account Limitations

    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
     ადა
    0.54
     стоковое
    0.53
     サマータイヤ
    0.52
     сотрудни
    0.50
    ଏ
    0.50
    lių
    0.49
    ៦
    0.49
    গ্রাফ
    0.48
     удовле
    0.48
     ৃ
    0.48
    POSITIVE LOGITS
     at
    0.48
     without
    0.48
     booklets
    0.45
    at
    0.45
     for
    0.45
    "
    0.44
    ت
    0.43
    ohl
    0.43
     Americans
    0.42
     M
    0.41
    Activations Density 0.018%

    No Known Activations