© 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. 30312
    Prev
    Next
    INDEX
    Explanations

    code and media context

    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
    őzés
    -0.78
     деятельность
    -0.72
     Germ
    -0.69
     Classifier
    -0.69
    idikan
    -0.68
    レム
    -0.67
    SerialPort
    -0.67
     Roundup
    -0.66
     octane
    -0.65
    uinal
    -0.65
    POSITIVE LOGITS
     PT
    0.75
     RULES
    0.68
     Fel
    0.65
    Besitos
    0.65
    Hx
    0.65
    )}{
    0.65
     FE
    0.65
    elfs
    0.64
     Jak
    0.64
    PT
    0.63
    Activations Density 0.080%

    No Known Activations