© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9440
    Prev
    Next
    INDEX
    Explanations

    public function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     when
    -0.92
     still
    -0.86
    定的
    -0.83
    жете
    -0.81
     if
    -0.80
    ̞
    -0.80
    リオン
    -0.78
    ||||
    -0.77
     U
    -0.76
     throughout
    -0.75
    POSITIVE LOGITS
    ₤
    1.04
    fting
    0.98
    Hva
    0.95
    Kaip
    0.95
    Kabel
    0.94
    дання
    0.92
    éndez
    0.92
    dstuk
    0.91
     ARISING
    0.91
    lierung
    0.90
    Activations Density 0.017%

    No Known Activations