© 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. 117335
    Prev
    Next
    INDEX
    Explanations

    ingredients and common text separators

    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
     angenehm
    -1.15
     comiendo
    -1.09
     disfrutando
    -1.05
     erila
    -1.01
     these
    -1.01
     präsenti
    -1.00
     luchando
    -1.00
     everyone
    -0.97
     apoyo
    -0.97
     vuelto
    -0.96
    POSITIVE LOGITS
     mixture
    1.11
     then
    1.09
     سپس
    1.04
     and
    0.98
    andoah
    0.97
    라고
    0.95
     потрібно
    0.92
     thoroughly
    0.91
    cetta
    0.91
     محفوظ
    0.91
    Activations Density 0.007%

    No Known Activations