© 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. 1051
    Prev
    Next
    INDEX
    Explanations

    utm parameters

    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
     listopada
    -0.77
    oun
    -0.71
    relli
    -0.71
    prnt
    -0.71
    gruntled
    -0.70
     vallée
    -0.70
     vinagre
    -0.69
    igli
    -0.68
    qJ
    -0.68
     krem
    -0.68
    POSITIVE LOGITS
    BSP
    0.81
     BSP
    0.79
     überweisen
    0.78
    SONS
    0.75
     servi
    0.75
     epoxy
    0.71
     mala
    0.71
    stuff
    0.70
     unspoken
    0.70
     ση
    0.69
    Activations Density 0.022%

    No Known Activations