© 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. 237981
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    纍
    0.46
     ভাষায়
    0.45
     Daarna
    0.44
     Anschließend
    0.44
     ನಂತರ
    0.43
    ート
    0.43
     Luego
    0.42
     ভাষায়
    0.41
    チュラル
    0.41
     ----->
    0.41
    POSITIVE LOGITS
    i
    0.51
    in
    0.50
    ва
    0.47
    ala
    0.46
    addock
    0.45
    isał
    0.44
    orum
    0.44
    ější
    0.44
    alf
    0.44
    ellä
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.