© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3968
    Prev
    Next
    INDEX
    Explanations

    All followed by lists

    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
     ОТ
    0.30
    IRCONIUM
    0.30
    ={`${
    0.28
     fibrils
    0.28
     زیرمه
    0.27
    羰
    0.26
     AFFAIRS
    0.26
    
    0.25
    stepToken
    0.25
    ENTES
    0.25
    POSITIVE LOGITS
    example
    0.50
     example
    0.50
     ejemplo
    0.50
     esempio
    0.46
     exemplo
    0.46
     exemple
    0.45
    foo
    0.42
     Example
    0.42
     Ejemplo
    0.41
    esempio
    0.41
    Activations Density 1.011%

    No Known Activations