© 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. 65194
    Prev
    Next
    INDEX
    Explanations

    BSD license // comments

    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
     թվական
    -0.68
     schwar
    -0.66
    BA
    -0.66
    ran
    -0.66
     Maud
    -0.65
     ägg
    -0.64
     Theolog
    -0.64
    bo
    -0.64
     handled
    -0.63
    autoload
    -0.63
    POSITIVE LOGITS
    stasy
    0.69
    箓
    0.68
    cello
    0.67
    trusive
    0.67
     kub
    0.67
    📔
    0.66
    infec
    0.66
    adec
    0.66
     teljes
    0.65
    preuve
    0.64
    Activations Density 0.059%

    No Known Activations