© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16438
    Prev
    Next
    INDEX
    Explanations

    geometric and temporal descriptors

    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
     and
    -1.37
     not
    -1.30
     which
    -1.02
     also
    -1.00
     something
    -0.99
     what
    -0.98
    D
    -0.93
    I
    -0.92
     toán
    -0.91
    </b>
    -0.88
    POSITIVE LOGITS
     interag
    1.25
    Ār
    1.16
     uovo
    1.09
     interro
    1.09
    ついに
    1.08
     serre
    1.06
     interwoven
    1.05
    Tetrach
    1.04
    actéristi
    1.04
    isés
    1.03
    Activations Density 0.068%

    No Known Activations