© 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. 29945
    Prev
    Next
    INDEX
    Explanations

    conditional "if" and "depending"

    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
    violet
    0.41
     بیشتری
    0.41
    ל
    0.40
     hyperactivity
    0.40
     appreciate
    0.39
    த்தர
    0.39
     sentiment
    0.39
    reonine
    0.39
     diction
    0.39
    は大
    0.39
    POSITIVE LOGITS
    كى
    0.54
    ମ୍
    0.47
    咡
    0.47
    ુપ
    0.45
    粑
    0.45
    的处理
    0.44
     accommodated
    0.43
     नज़र
    0.42
    quitos
    0.42
     megfelelő
    0.42
    Activations Density 0.004%

    No Known Activations