© 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. 90118
    Prev
    Next
    INDEX
    Explanations

    motivational, construction, proper names

    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
     fonds
    -0.81
     emis
    -0.79
     Mend
    -0.78
    Trey
    -0.70
     Median
    -0.69
     Parac
    -0.69
    ceptor
    -0.69
    тивний
    -0.69
    inga
    -0.68
     parad
    -0.67
    POSITIVE LOGITS
     competence
    0.85
    ;?>
    0.85
    kolog
    0.82
    autonomous
    0.80
    AGAN
    0.80
     amo
    0.80
     controlador
    0.78
    ㈠
    0.77
     ought
    0.76
    koda
    0.76
    Activations Density 0.032%

    No Known Activations