© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103153
    Prev
    Next
    INDEX
    Explanations

    delivering goods, services, or outcomes

    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_10/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
     інших
    -2.11
     dekoratif
    -2.02
    junctive
    -2.00
    횃
    -1.88
     різних
    -1.84
    頹
    -1.83
    autorelease
    -1.78
    就像是
    -1.72
    Beskrivning
    -1.68
    徬
    -1.68
    POSITIVE LOGITS
     –
    2.08
     and
    1.91
    </em>
    1.73
    li
    1.65
    (
    1.52
    >
    1.52
        
    1.48
    In
    1.41
    {
    1.40
     followed
    1.38
    Activations Density 0.010%

    No Known Activations