© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73459
    Prev
    Next
    INDEX
    Explanations

    what exactly, why exactly

    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
    Lain
    -1.52
    Ruj
    -1.45
     esponja
    -1.31
    Makanan
    -1.29
     sufficient
    -1.26
     asesinado
    -1.25
    Makan
    -1.23
    ሣ
    -1.23
    Hapana
    -1.23
     esbo
    -1.21
    POSITIVE LOGITS
     how
    2.23
     why
    1.76
     these
    1.64
     they
    1.58
     are
    1.58
     what
    1.47
    is
    1.45
    U
    1.40
     you
    1.40
    –
    1.39
    Activations Density 0.013%

    No Known Activations