© 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. 65029
    Prev
    Next
    INDEX
    Explanations

    Copyright and licenses

    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
    呷
    -0.83
    Amid
    -0.77
    見え
    -0.76
    amid
    -0.73
     sueños
    -0.71
    醸
    -0.71
     tumultuous
    -0.71
     brimming
    -0.70
     móc
    -0.70
     hallaz
    -0.70
    POSITIVE LOGITS
     spruce
    0.81
    willReturn
    0.79
    ESTY
    0.75
    ASING
    0.74
     sharpening
    0.74
    Monsters
    0.72
     lettere
    0.71
     conter
    0.71
     Mandy
    0.71
    зах
    0.71
    Activations Density 1.112%

    No Known Activations