© 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. 76550
    Prev
    Next
    INDEX
    Explanations

    specifying conditions

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

    conclusions or reasons

    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
    с
    0.57
    これにより
    0.48
    孫
    0.45
    ┅
    0.45
     মুখোমুখি
    0.45
    再び
    0.43
    ください
    0.42
     VGM
    0.41
    銘
    0.41
    ｰ
    0.41
    POSITIVE LOGITS
     varit
    0.54
    なので
    0.47
     demonstrable
    0.46
     যাহা
    0.46
     sowas
    0.46
     vergleich
    0.45
    edores
    0.44
     पीछे
    0.42
     svært
    0.41
    লাইয়া
    0.41
    Activations Density 0.002%

    No Known Activations