© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1655
    Prev
    Next
    INDEX
    Explanations

    uncertainty

    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_10/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
    ⻬
    -2.31
     baffling
    -1.92
    leggio
    -1.90
    creating
    -1.84
     paltry
    -1.82
    genodigd
    -1.80
     Когда
    -1.79
    zmm
    -1.75
     vitales
    -1.75
    Eventually
    -1.74
    POSITIVE LOGITS
    or
    2.09
    t
    1.98
    there
    1.90
    e
    1.84
    but
    1.81
     about
    1.80
     there
    1.79
     in
    1.75
     uncertain
    1.70
    use
    1.68
    Activations Density 0.018%

    No Known Activations