© 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. 59470
    Prev
    Next
    INDEX
    Explanations

    amount of

    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
     valutazione
    -1.05
     that
    -1.04
     daarom
    -1.04
     suficientemente
    -1.00
     zoveel
    -0.99
     ontvang
    -0.98
     galore
    -0.97
    倹
    -0.96
    ITCHEN
    -0.95
     waarmee
    -0.95
    POSITIVE LOGITS
     of
    2.11
     (>
    1.06
    nés
    1.06
     antici
    1.00
     Préférences
    1.00
    ه‌اند
    0.99
     veta
    0.98
     favorita
    0.98
    maschine
    0.96
     dritte
    0.96
    Activations Density 0.055%

    No Known Activations