© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3111
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

    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
     So
    -0.91
     For
    -0.90
     To
    -0.85
     А
    -0.81
     $\
    -0.81
     This
    -0.81
    ea
    -0.81
     ост
    -0.81
     Buena
    -0.80
     And
    -0.80
    POSITIVE LOGITS
    ↵↵
    1.47
    );
    0.90
    yaf
    0.89
    Général
    0.87
    supposed
    0.84
     анге
    0.81
     外観
    0.81
    useless
    0.81
    Guardar
    0.80
     posiciones
    0.79
    Activations Density 0.688%

    No Known Activations