© 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. 57220
    Prev
    Next
    INDEX
    Explanations

    purpose or context

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

    for use cases

    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
    可以让
    0.55
     ويمكن
    0.51
     يمكنك
    0.49
    ଂ
    0.49
    克兰
    0.47
     Você
    0.46
    ための
    0.46
    ほか
    0.46
     możesz
    0.46
    ☓
    0.45
    POSITIVE LOGITS
    dir
    0.45
     fieldwork
    0.42
     standardize
    0.42
     रहीं
    0.41
     campaigning
    0.41
     volunteering
    0.40
    ponym
    0.40
     standar
    0.40
     archiving
    0.40
     rehearsals
    0.40
    Activations Density 0.048%

    No Known Activations