© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15850
    Prev
    Next
    INDEX
    Explanations

    for (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     stemming
    0.67
     estimators
    0.65
     నాగ
    0.62
     〔
    0.62
     известные
    0.61
    тной
    0.61
     Weyl
    0.60
     uitgebre
    0.60
     estimados
    0.59
     i
    0.59
    POSITIVE LOGITS
    返す
    0.60
    FromString
    0.55
    !",
    0.55
    !',
    0.54
     res
    0.51
    String
    0.51
     !"
    0.50
     !",
    0.50
    শা
    0.49
    ビデオ
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.