© 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. 106228
    Prev
    Next
    INDEX
    Explanations

    quantity and purpose

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

    context generation

    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
     pertenece
    0.49
    籲
    0.48
    ется
    0.47
    يت
    0.47
     लाई
    0.46
    operated
    0.46
     Equitable
    0.45
     nije
    0.45
     participates
    0.44
     competes
    0.44
    POSITIVE LOGITS
    帚
    0.51
    닼
    0.50
     TYPES
    0.49
     подума
    0.48
     OUTPUT
    0.48
    례
    0.45
    驩
    0.44
    lık
    0.44
     CORRECT
    0.44
     obtención
    0.44
    Activations Density 0.001%

    No Known Activations