© 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. 10-GEMMASCOPE-RES-131K
    7. 58944
    Prev
    Next
    INDEX
    Explanations

    naming declared properties

    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_10/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
     also
    -2.64
     
    -2.25
     promotes
    -2.14
     allow
    -2.08
     removes
    -2.02
     maintains
    -2.00
     provide
    -2.00
     enhance
    -1.99
     as
    -1.98
     helps
    -1.97
    POSITIVE LOGITS
     både
    2.30
     AMAZING
    2.11
     the
    2.05
     unſ
    1.98
     insanely
    1.92
     immen
    1.90
     magnificent
    1.90
     incrí
    1.89
     amazingly
    1.88
    amazing
    1.84
    Activations Density 0.008%

    No Known Activations