© 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. 48769
    Prev
    Next
    INDEX
    Explanations

    instructions, communication, requirements

    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
    силання
    0.48
    欧元
    0.47
     Phật
    0.46
    organizzazione
    0.46
    勍
    0.46
    佛教
    0.46
    激素
    0.45
    OpportunitiesBy
    0.45
    ค้า
    0.44
    蓝牙
    0.44
    POSITIVE LOGITS
     data
    0.53
     full
    0.51
     the
    0.50
     offset
    0.47
     =
    0.46
     origin
    0.46
     input
    0.45
     high
    0.45
     mens
    0.45
     observe
    0.45
    Activations Density 0.001%

    No Known Activations