© 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. 5034
    Prev
    Next
    INDEX
    Explanations

    call to action or transition phrases

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

    German compounds

    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
    鸪
    0.50
     Sales
    0.46
     thự
    0.46
     ۱۰
    0.46
    覓
    0.45
     господар
    0.45
    ائية
    0.44
     Ñ
    0.43
     offensively
    0.43
     Thief
    0.43
    POSITIVE LOGITS
    Gö
    0.51
    Classe
    0.48
    ರೆ
    0.47
    addElement
    0.47
     ArrayIndex
    0.47
    POD
    0.47
     piti
    0.47
    ங்களும்
    0.46
     doubtful
    0.46
    sset
    0.46
    Activations Density 0.000%

    No Known Activations