© 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. 40533
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by specific words

    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
     phá
    0.50
     clergyman
    0.47
     ショルダーバッグ
    0.47
    <0xB2>
    0.46
    IsResolver
    0.46
     Unlock
    0.45
     Theological
    0.45
    ंत्रिकी
    0.44
    ೊಂದು
    0.43
     backpacking
    0.43
    POSITIVE LOGITS
    ERS
    0.52
     NIS
    0.43
     meinen
    0.41
    ニス
    0.41
     SSI
    0.41
    大
    0.41
     మీడి
    0.40
     CSI
    0.40
     zug
    0.39
    عادة
    0.39
    Activations Density 0.005%

    No Known Activations