© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 31083
    Prev
    Next
    INDEX
    Explanations

    founder and president titles

    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
     they
    -1.19
    を行いました
    -1.14
    t
    -1.14
    这不
    -1.11
     careful
    -1.10
     aceea
    -1.09
    G
    -1.07
    f
    -1.07
     little
    -1.06
    alers
    -1.06
    POSITIVE LOGITS
     of
    5.84
    ของ
    2.45
     của
    2.27
     and
    1.99
     at
    1.64
     של
    1.63
     της
    1.45
    تحميل
    1.30
     των
    1.29
     ofthe
    1.29
    Activations Density 0.044%

    No Known Activations