© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55813
    Prev
    Next
    INDEX
    Explanations

    version numbers 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
    स
    -0.81
    С
    -0.80
    ="#"
    -0.79
    parentNode
    -0.75
     unparalleled
    -0.71
     unpopular
    -0.70
    NSMutableArray
    -0.68
    У
    -0.67
    madores
    -0.67
    SqlCommand
    -0.65
    POSITIVE LOGITS
    应当
    0.72
    GW
    0.68
    ulty
    0.67
     Nugent
    0.67
     ausreichend
    0.67
    χε
    0.67
     진
    0.67
    醮
    0.66
    撂
    0.66
    :*
    0.66
    Activations Density 0.536%

    No Known Activations