© 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. 37030
    Prev
    Next
    INDEX
    Explanations

    service descriptions

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

    long inputs and documents

    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
     antibiot
    0.48
     rabbi
    0.48
    ｵ
    0.47
     assis
    0.47
    ﾇ
    0.46
     учитель
    0.46
     राउ
    0.45
     বন্দরে
    0.45
     деца
    0.45
     petición
    0.45
    POSITIVE LOGITS
     Funktion
    0.47
    ↵
    0.47
     spreading
    0.46
     damn
    0.46
     foreshadow
    0.45
     pinching
    0.45
     snapped
    0.44
     working
    0.44
     fores
    0.44
     scalp
    0.43
    Activations Density 0.000%

    No Known Activations