© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 49970
    Prev
    Next
    INDEX
    Explanations

    license file paths and URLs

    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
     userService
    -0.70
    camento
    -0.68
    ఉ
    -0.67
     geométrico
    -0.67
    çal
    -0.66
    ütten
    -0.66
     Roux
    -0.66
     Gesch
    -0.65
     byteArray
    -0.63
    akka
    -0.63
    POSITIVE LOGITS
     highland
    0.72
    Keine
    0.69
    ffix
    0.68
    HBO
    0.67
    ix
    0.66
     VBA
    0.66
    тических
    0.66
    缓冲
    0.65
     Metadata
    0.65
     PROV
    0.65
    Activations Density 0.106%

    No Known Activations