© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2420
    Prev
    Next
    INDEX
    Explanations

    subscripts and superscripts

    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
     reduces
    -0.90
     taking
    -0.85
    Several
    -0.84
     tdci
    -0.84
    Generally
    -0.84
    ごろ
    -0.84
     which
    -0.83
     reducing
    -0.82
     several
    -0.82
     allowing
    -0.82
    POSITIVE LOGITS
    COMMENT
    1.13
     flexibel
    1.10
     opérateur
    1.10
    comment
    1.08
    block
    1.07
     блок
    0.96
     ネック
    0.96
     praticamente
    0.93
     dobre
    0.93
    \}=\
    0.93
    Activations Density 0.001%

    No Known Activations