© 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. 55857
    Prev
    Next
    INDEX
    Explanations

    html context

    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
    zación
    -0.71
    ₸
    -0.68
    toolbar
    -0.67
     Modesto
    -0.66
     wx
    -0.65
    tribe
    -0.64
     Dissolve
    -0.63
    Radiation
    -0.63
    写入
    -0.63
     Nail
    -0.63
    POSITIVE LOGITS
    piration
    0.75
     Gallup
    0.69
    calibration
    0.68
     Jiao
    0.68
    iels
    0.68
    igraphic
    0.65
    ometrics
    0.65
     nghiệm
    0.65
     Duval
    0.64
    lsen
    0.63
    Activations Density 0.095%

    No Known Activations