© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9769
    Prev
    Next
    INDEX
    Explanations

    par exemple, par ailleurs, par dessus

    np_acts-logits-general · gemini-2.5-flash-lite

    por followed by qué, sobre, debajo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     диви
    0.44
     प्रीत
    0.44
     칼
    0.43
     ట
    0.43
     沖縄
    0.42
     οπο
    0.41
     tonnage
    0.41
     लवकर
    0.41
    䢁
    0.40
     판
    0.40
    POSITIVE LOGITS
    type
    0.50
    input
    0.49
    scoped
    0.47
    end
    0.46
    def
    0.46
    Throw
    0.46
    points
    0.46
    par
    0.45
    big
    0.45
    paragraph
    0.45
    Activations Density 0.003%

    No Known Activations