© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48934
    Prev
    Next
    INDEX
    Explanations

    code and annotation

    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
     Ashes
    -0.72
     sprink
    -0.71
    /*
    -0.69
     instants
    -0.67
     broadcasts
    -0.67
    чої
    -0.66
    apor
    -0.66
     り
    -0.66
    Arena
    -0.65
    chantment
    -0.65
    POSITIVE LOGITS
    hya
    0.70
    drums
    0.68
    traum
    0.67
    yak
    0.66
     ruby
    0.65
    olle
    0.63
     Zub
    0.63
     HY
    0.62
     voter
    0.62
     Lucie
    0.61
    Activations Density 0.099%

    No Known Activations