© 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. 54051
    Prev
    Next
    INDEX
    Explanations

    her or his followed by associated nouns

    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
    corrhi
    -1.64
     terke
    -1.62
    €”
    -1.56
     porcent
    -1.55
    Ⲉ
    -1.52
    кроссовки
    -1.52
    mentar
    -1.51
     amie
    -1.50
     franca
    -1.50
    FFECT
    -1.50
    POSITIVE LOGITS
     also
    2.75
     is
    2.20
    そして
    1.73
    irs
    1.72
    ’
    1.66
     to
    1.60
     was
    1.59
    などを
    1.49
     then
    1.46
     result
    1.46
    Activations Density 0.046%

    No Known Activations