© 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. 117631
    Prev
    Next
    INDEX
    Explanations

    version numbers and software licenses

    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
    PopupMenu
    -0.82
    unggulan
    -0.82
     quoque
    -0.81
    🍸
    -0.80
    ostringstream
    -0.80
    lope
    -0.79
    🔗
    -0.76
    clips
    -0.76
    CURLOPT
    -0.75
     Georgie
    -0.75
    POSITIVE LOGITS
     noastre
    0.88
     vieille
    0.81
     Pilgrim
    0.80
    nickName
    0.79
    Continu
    0.75
    SaveVideo
    0.75
     adecuado
    0.74
    trường
    0.74
    Ini
    0.74
    APRIL
    0.74
    Activations Density 0.040%

    No Known Activations