© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107909
    Prev
    Next
    INDEX
    Explanations

    license, code, section, or number

    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
     checking
    -0.73
     evacuate
    -0.70
    Xf
    -0.66
     cuál
    -0.66
     检查
    -0.66
     JOIN
    -0.66
    edc
    -0.65
    alleye
    -0.65
    check
    -0.64
    rescue
    -0.63
    POSITIVE LOGITS
     inactivity
    0.69
     Emerald
    0.68
     बनाने
    0.66
    GRANTED
    0.66
     букет
    0.66
    banden
    0.66
    Emerald
    0.65
    嚐
    0.65
    ungkap
    0.65
     prologue
    0.64
    Activations Density 0.036%

    No Known Activations