© 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. 22-GEMMASCOPE-RES-131K
    7. 547
    Prev
    Next
    INDEX
    Explanations

    is followed by that

    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_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
    leiding
    -1.66
     tegens
    -1.48
    ėti
    -1.37
     sommige
    -1.31
     gemeenten
    -1.29
    tierte
    -1.26
    beyaz
    -1.25
     тыся
    -1.24
     and
    -1.23
    ølge
    -1.23
    POSITIVE LOGITS
     to
    3.39
     that
    2.97
     not
    1.89
     a
    1.75
     about
    1.70
     now
    1.69
     being
    1.68
     what
    1.66
     how
    1.58
     actually
    1.51
    Activations Density 0.051%

    No Known Activations