© 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. 184233
    Prev
    Next
    INDEX
    Explanations

    unique as you are

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

    contextual qualifiers

    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
     Seymour
    0.47
    dataFormat
    0.45
     aspects
    0.43
     stif
    0.43
     Format
    0.42
    WordPress
    0.42
     Marcos
    0.41
    껐
    0.41
     scaff
    0.40
    ništ
    0.40
    POSITIVE LOGITS
    女
    0.51
     `>`,
    0.50
     fyrir
    0.50
    enteuer
    0.50
     dãy
    0.49
    க்கிழ
    0.49
     mujer
    0.47
     빠르게
    0.46
     innehåller
    0.46
    𒌉
    0.46
    Activations Density 0.001%

    No Known Activations