© 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. 74510
    Prev
    Next
    INDEX
    Explanations

    sharing information online

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

    screen, bringing, needing, creating

    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
    ван
    0.52
     等
    0.50
    迲
    0.48
     możliwość
    0.46
     肩
    0.46
     شوند
    0.46
    াড়া
    0.46
     lehet
    0.45
     tolerancia
    0.45
    図
    0.45
    POSITIVE LOGITS
     reformed
    0.46
    solved
    0.43
     insects
    0.43
    独自の
    0.42
    鄉
    0.42
    ुत
    0.41
     transformations
    0.41
     tourists
    0.40
     almond
    0.40
     मुझ
    0.40
    Activations Density 0.001%

    No Known Activations