© 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. 11216
    Prev
    Next
    INDEX
    Explanations

    legal terms and lists

    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
    apartament
    -0.97
    entur
    -0.85
    angling
    -0.85
    zmm
    -0.84
    andingan
    -0.82
    Karakter
    -0.82
     aucune
    -0.82
    ifx
    -0.80
    やう
    -0.79
    Ď
    -0.79
    POSITIVE LOGITS
    delmi
    0.89
    in
    0.80
    f
    0.78
     tx
    0.78
    l
    0.77
    む
    0.77
    õ
    0.76
    au
    0.76
    r
    0.75
    a
    0.75
    Activations Density 0.059%

    No Known Activations