© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 25642
    Prev
    Next
    INDEX
    Explanations

    years and periods

    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
     or
    -1.88
     now
    -1.37
     what
    -1.30
     as
    -1.29
     wants
    -1.28
     think
    -1.27
     already
    -1.23
     is
    -1.23
     to
    -1.20
     also
    -1.18
    POSITIVE LOGITS
     alatt
    1.33
     siè
    1.32
    ⁓
    1.30
     boyunca
    1.29
    ⎩
    1.28
     vermel
    1.25
    椋
    1.23
    etna
    1.23
     chanteur
    1.23
     rése
    1.21
    Activations Density 0.049%

    No Known Activations