© 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. 10-GEMMASCOPE-RES-131K
    7. 59740
    Prev
    Next
    INDEX
    Explanations

    I can say

    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_10/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
    ⛦
    -1.85
     enregistrer
    -1.59
     Añade
    -1.55
     Permite
    -1.53
     皇族
    -1.47
    噲
    -1.46
     ถ้า
    -1.44
    ACCIÓN
    -1.44
     rafra
    -1.44
    afficheront
    -1.43
    POSITIVE LOGITS
     we
    2.03
     for
    1.67
     that
    1.60
     of
    1.55
     \
    1.53
    e
    1.48
     particularly
    1.44
     dikutip
    1.42
     каждого
    1.41
    –
    1.38
    Activations Density 0.008%

    No Known Activations