© 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. 10-GEMMASCOPE-RES-131K
    7. 69192
    Prev
    Next
    INDEX
    Explanations

    unfavorable or disfavored situations

    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
    Although
    -1.55
    Despite
    -1.55
     doubtless
    -1.55
     touted
    -1.52
    ៚
    -1.49
    People
    -1.48
    chaub
    -1.48
     –
    -1.48
    Though
    -1.46
    After
    -1.45
    POSITIVE LOGITS
    it
    1.90
    3
    1.65
    2
    1.58
    -&
    1.55
     you
    1.55
    也要
    1.53
    for
    1.45
    </
    1.44
    t
    1.44
    𐐀
    1.41
    Activations Density 0.082%

    No Known Activations