© 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. 134217
    Prev
    Next
    INDEX
    Explanations

    technical and transactional verbs

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

    note followed by detail

    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
     aprend
    0.55
     Señor
    0.49
     배웠
    0.49
     tarea
    0.49
     Aprend
    0.47
    ق
    0.46
     Tạo
    0.46
    ।
    0.46
     Brown
    0.46
     aprender
    0.45
    POSITIVE LOGITS
    spirit
    0.48
    Bombay
    0.47
    非常に
    0.46
    者の
    0.45
    ہری
    0.45
    account
    0.44
     ചെയ്യുന്ന
    0.43
     нака
    0.43
    இந்திய
    0.43
    ברה
    0.43
    Activations Density 0.000%

    No Known Activations