© 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. 108067
    Prev
    Next
    INDEX
    Explanations

    uniform resource identifiers

    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
    柳
    -0.71
     числе
    -0.69
    tanleria
    -0.66
     llave
    -0.66
    AYER
    -0.66
     مركز
    -0.66
     Mentions
    -0.66
     gasped
    -0.66
     Gamb
    -0.65
    BON
    -0.64
    POSITIVE LOGITS
     URI
    2.09
     Uri
    1.84
    URI
    1.70
     uri
    1.63
    Uri
    1.57
     Uniform
    1.46
    uri
    1.22
    Uniform
    1.16
     UR
    1.06
    IRI
    1.05
    Activations Density 0.067%

    No Known Activations