© 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. 93253
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    This
    -0.83
     diretor
    -0.79
     ajouté
    -0.77
     know
    -0.76
    CHEZ
    -0.76
    現在
    -0.75
    They
    -0.75
     menschliche
    -0.75
    をご覧ください
    -0.75
    发布于
    -0.75
    POSITIVE LOGITS
    ACADEM
    0.84
    élève
    0.81
     Verify
    0.81
    GUAR
    0.81
    での
    0.81
     ongel
    0.80
     برج
    0.80
    duit
    0.79
    zną
    0.79
    ัต
    0.79
    Activations Density 0.009%

    No Known Activations