© 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. 181629
    Prev
    Next
    INDEX
    Explanations

    infin or elect

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

    in common phrases

    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
     percorso
    0.49
     provoz
    0.47
    тиви
    0.47
     przeg
    0.46
     Sms
    0.45
     фо
    0.45
    泗
    0.45
     obrigado
    0.45
     afge
    0.44
     przep
    0.43
    POSITIVE LOGITS
    haviours
    0.48
    case
    0.47
    LOT
    0.46
    ۲
    0.45
            
    0.45
                
    0.45
    form
    0.45
    between
    0.45
    formal
    0.43
    ₹
    0.43
    Activations Density 0.002%

    No Known Activations