© 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. 57201
    Prev
    Next
    INDEX
    Explanations

    numbers, punctuation, special characters

    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
     collaborators
    -0.85
    новых
    -0.82
     Эта
    -0.81
     стены
    -0.81
     ..
    -0.81
     ڤ
    -0.79
     diesen
    -0.79
     //
    -0.78
    стема
    -0.77
    GRAFÍA
    -0.77
    POSITIVE LOGITS
     then
    0.94
    λισ
    0.86
    calça
    0.86
     determinado
    0.85
     gebunden
    0.85
    扺
    0.85
    Legenda
    0.84
    Затем
    0.83
     îng
    0.80
     arrivée
    0.80
    Activations Density 0.002%

    No Known Activations