© 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. 34-GEMMASCOPE-RES-131K
    4. 2339
    Prev
    Next
    INDEX
    Explanations

    public function declarations

    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_34/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
    makeatother
    -0.85
     {@
    -0.85
     aktiven
    -0.83
     later
    -0.81
    premier
    -0.81
    ansons
    -0.80
    特意
    -0.79
     czter
    -0.79
     mudou
    -0.78
     discriminación
    -0.78
    POSITIVE LOGITS
     array
    1.24
     string
    1.14
    string
    1.09
    iterable
    1.09
    array
    1.06
     stolet
    0.97
     ?
    0.96
     iterable
    0.94
     mixed
    0.94
     float
    0.91
    Activations Density 0.005%

    No Known Activations