© 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. 116957
    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
    ⅙
    -0.94
     triliun
    -0.93
     =>
    -0.91
     Vaters
    -0.90
    ම
    -0.90
     just
    -0.87
    ⅘
    -0.86
    ⅖
    -0.84
     for
    -0.83
    城的
    -0.81
    POSITIVE LOGITS
     function
    2.02
    function
    1.81
     functions
    1.20
     public
    1.13
     fonction
    1.11
    FUNCTION
    1.09
    función
    1.09
    public
    1.08
     Function
    1.07
     funzione
    1.06
    Activations Density 0.011%

    No Known Activations