© 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. 22-GEMMASCOPE-RES-131K
    7. 129315
    Prev
    Next
    INDEX
    Explanations

    French phrases

    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_22/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
    It
    -2.09
    L
    -2.05
    In
    -1.84
     There
    -1.83
    M
    -1.82
    R
    -1.80
    E
    -1.77
     Since
    -1.77
     as
    -1.73
     use
    -1.73
    POSITIVE LOGITS
     trám
    1.80
    และ
    1.76
    ſſen
    1.73
     célè
    1.65
     mauva
    1.61
    
    1.59
    ₶
    1.58
    鸲
    1.56
     plafon
    1.55
     zoude
    1.55
    Activations Density 0.036%

    No Known Activations