© 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. 3803
    Prev
    Next
    INDEX
    Explanations

    realistic detail and digital

    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
    ח
    0.50
     માહિતી
    0.48
     হ
    0.48
     SEN
    0.47
     decompose
    0.47
     recrut
    0.46
     metastatic
    0.46
     cambia
    0.46
    recruit
    0.46
     હો
    0.45
    POSITIVE LOGITS
     छह
    0.44
    ül
    0.43
    晨
    0.43
    phenol
    0.42
     দাঁড়
    0.42
    itiv
    0.41
    ³
    0.41
    
    0.41
    ulé
    0.40
    ισμού
    0.40
    Activations Density 0.001%

    No Known Activations