© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9773
    Prev
    Next
    INDEX
    Explanations

    all

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags terms you’d find in concrete product or service specs—price/shipping/VAT language, numeric measurements, and other detailed feature listings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     perhaps
    -1.52
     it
    -1.47
     might
    -1.44
     when
    -1.36
     many
    -1.28
     may
    -1.25
     maybe
    -1.25
     kanske
    -1.23
     then
    -1.20
     during
    -1.20
    POSITIVE LOGITS
    either
    1.95
    Either
    1.76
     their
    1.73
     entweder
    1.69
    Except
    1.55
    要么
    1.54
     either
    1.50
     except
    1.48
     mindestens
    1.44
    except
    1.43
    Activations Density 0.121%

    No Known Activations