© 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. 32614
    Prev
    Next
    INDEX
    Explanations

    image scale factors

    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
    нного
    -0.74
     phu
    -0.73
     supre
    -0.71
     Spectral
    -0.70
     Fum
    -0.69
     точку
    -0.68
    DataStore
    -0.68
     Righ
    -0.68
    chauung
    -0.68
     spectral
    -0.66
    POSITIVE LOGITS
     Nine
    0.84
     clipping
    0.81
    九
    0.79
     Oklahoma
    0.79
    Nine
    0.78
     Worlds
    0.76
     Richie
    0.73
    Cli
    0.72
    Vanjske
    0.71
    liced
    0.71
    Activations Density 0.032%

    No Known Activations