© 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. 64942
    Prev
    Next
    INDEX
    Explanations

    studies and data analysis

    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
     can
    -1.48
     first
    -1.43
     is
    -1.38
     as
    -1.30
     even
    -1.29
     without
    -1.28
     now
    -1.27
     may
    -1.25
     will
    -1.23
    POSITIVE LOGITS
     Pristup
    1.55
     camiset
    1.55
     merve
    1.41
     GARANT
    1.41
     péro
    1.38
     kijang
    1.37
     разных
    1.35
    傒
    1.34
     corrom
    1.34
     köy
    1.34
    Activations Density 0.150%

    No Known Activations