© 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. 84693
    Prev
    Next
    INDEX
    Explanations

    grammatical markers

    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
    ne
    0.46
     torment
    0.45
    ډ
    0.45
    would
    0.44
    ľa
    0.43
    ピ
    0.43
    credentials
    0.43
    <0xE2>
    0.42
    си
    0.42
    ights
    0.42
    POSITIVE LOGITS
    暂停
    0.47
     pausing
    0.43
     covenants
    0.43
    的服务
    0.42
     Determines
    0.42
     liée
    0.42
    服务
    0.41
     poświę
    0.41
     seasonings
    0.40
    的时候
    0.40
    Activations Density 0.004%

    No Known Activations