© 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. 233106
    Prev
    Next
    INDEX
    Explanations

    simply insert

    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
     Verfügung
    0.47
    ية
    0.45
    向上
    0.43
     المؤمن
    0.43
    暠
    0.42
     mamy
    0.41
     Gerade
    0.41
     tính
    0.41
     egen
    0.41
    炅
    0.41
    POSITIVE LOGITS
     सरकारच्या
    0.52
     fatigue
    0.47
    сторія
    0.47
    ᱼ
    0.46
    엥
    0.46
     corruption
    0.45
     disusun
    0.45
     звез
    0.45
    撓
    0.45
     TRUST
    0.44
    Activations Density 0.001%

    No Known Activations