© 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. 48364
    Prev
    Next
    INDEX
    Explanations

    specific conditions with 'of'

    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
    铰
    -1.02
     და
    -0.99
     ignor
    -0.92
    straat
    -0.92
    entibus
    -0.86
     gratis
    -0.86
     polypep
    -0.85
    ;';
    -0.85
    theon
    -0.82
    causing
    -0.82
    POSITIVE LOGITS
     hearing
    1.37
     Hearing
    1.25
     breast
    1.22
     sleep
    1.15
     hair
    1.15
    Hearing
    1.08
     foot
    1.06
     eye
    1.04
     stroke
    1.04
     diabetic
    1.02
    Activations Density 0.901%

    No Known Activations