© 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. 25420
    Prev
    Next
    INDEX
    Explanations

    playful, happy, shared, meters, xml

    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
    ní
    0.53
    ə
    0.52
    ánea
    0.50
    𝐝
    0.48
     этап
    0.47
     races
    0.46
    ୀ
    0.46
     temptation
    0.46
    
    0.46
     transgression
    0.45
    POSITIVE LOGITS
    籬
    0.48
    Caf
    0.41
    Soup
    0.40
    Collider
    0.39
    Pregnant
    0.39
    Though
    0.38
    widgets
    0.38
    Coffee
    0.38
     වලින්
    0.38
    Filled
    0.38
    Activations Density 0.003%

    No Known Activations