© 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. 12430
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
    了你
    -1.44
    righteous
    -1.35
    Obr
    -1.35
     Winaray
    -1.34
     escuchado
    -1.32
    transpiration
    -1.29
    Scienti
    -1.28
    excellents
    -1.26
     demostrado
    -1.25
    dolphin
    -1.23
    POSITIVE LOGITS
    ();
    1.57
     it
    1.45
    N
    1.37
    ("");
    
    1.37
     they
    1.36
    ;
    
    1.32
    }}_{\
    1.26
    çamento
    1.25
    هاي
    1.24
     baseman
    1.24
    Activations Density 0.009%

    No Known Activations