© 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. 72302
    Prev
    Next
    INDEX
    Explanations

    starts questions or addresses

    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
    ﷻ
    -1.20
    anía
    -1.18
    })=\
    -1.18
    bonsoir
    -1.16
     tersebut
    -1.14
    "),
    -1.14
     $"
    -1.14
     <>",
    -1.14
    ſtra
    -1.13
    áját
    -1.13
    POSITIVE LOGITS
     really
    1.79
     things
    1.62
     people
    1.59
     дуже
    1.55
     there
    1.55
     we
    1.52
     очень
    1.52
     veldig
    1.45
     kinds
    1.43
     very
    1.40
    Activations Density 0.007%

    No Known Activations