© 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. 120941
    Prev
    Next
    INDEX
    Explanations

    awesome

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

    positive sentiment across languages

    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
     aspect
    0.40
    経営
    0.40
     aspecto
    0.40
    pecies
    0.38
    ारा
    0.38
    *>(
    0.38
    EnableWeb
    0.37
    ୮
    0.37
     aspek
    0.37
    виться
    0.37
    POSITIVE LOGITS
    我很
    0.48
    öz
    0.46
     அவரின்
    0.42
     மிகுந்த
    0.41
     Fighters
    0.41
    이었
    0.41
     शानदार
    0.41
    adığı
    0.40
     यादगार
    0.40
     দুর্দান্ত
    0.40
    Activations Density 0.006%

    No Known Activations