© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1064
    Prev
    Next
    INDEX
    Explanations

    dates and prices

    np_acts-logits-general · gemini-2.5-flash-lite

    levels and costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BROWN
    0.30
     waterfowl
    0.30
     fluids
    0.29
    HCO
    0.29
     carcasses
    0.29
     naszych
    0.29
     अणुओं
    0.29
    >∕
    0.29
     Bacter
    0.29
     ventilation
    0.28
    POSITIVE LOGITS
    ↵
    0.30
     validType
    0.29
     اكتب
    0.28
     write
    0.28
            
    0.28
     GoName
    0.28
    <0xE3>
    0.27
        
    0.27
     inoltre
    0.27
                 
    0.26
    Activations Density 0.084%

    No Known Activations