© 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. 47725
    Prev
    Next
    INDEX
    Explanations

    P.S. and btw abbreviations

    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
    جوايز
    -0.81
    スポンサーリンク
    -0.81
     Palmer
    -0.77
    Peptide
    -0.75
    قدم
    -0.75
     jätte
    -0.75
     blockSize
    -0.73
     Zapo
    -0.72
    спасибо
    -0.72
    𝘨
    -0.71
    POSITIVE LOGITS
     PS
    5.13
    PS
    4.88
     ps
    4.31
    ps
    3.81
     Ps
    3.61
    Ps
    3.30
    pS
    2.44
     btw
    2.38
     BTW
    2.30
    BTW
    2.08
    Activations Density 0.125%

    No Known Activations