© 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. 178922
    Prev
    Next
    INDEX
    Explanations

    phrases about temporal or distributive quantities

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

    conversational phrases and descriptions

    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
    ボリューム
    0.54
     আমরা
    0.50
     ਪਰ
    0.49
     우리가
    0.49
    ᑉ
    0.49
    paragraphs
    0.48
    ၌
    0.48
    STE
    0.47
    いくつかの
    0.47
    surface
    0.46
    POSITIVE LOGITS
        
    0.50
     Redwood
    0.48
    soever
    0.48
     Marzo
    0.48
     sor
    0.47
     Biss
    0.46
     Dole
    0.46
     spe
    0.46
    Méd
    0.46
     rus
    0.45
    Activations Density 0.000%

    No Known Activations