© 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. 108140
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases

    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
    ง
    0.48
    Helvetica
    0.47
     এরই
    0.44
    ༣
    0.43
    DEBUG
    0.43
    ުގައި
    0.42
    Filename
    0.42
    हिंदी
    0.42
     timed
    0.41
    軟
    0.41
    POSITIVE LOGITS
     Ehm
    0.54
     '*
    0.45
     궁금
    0.44
    onos
    0.43
     lorf
    0.42
     φυ
    0.42
    有没有
    0.42
     custodians
    0.42
     cuando
    0.42
     porod
    0.42
    Activations Density 0.002%

    No Known Activations