© 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. 7802
    Prev
    Next
    INDEX
    Explanations

    what does it mean

    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
    粜
    -1.55
     enorme
    -1.54
    archiwizowane
    -1.52
     a
    -1.51
     сможете
    -1.50
    really
    -1.49
     dvou
    -1.46
     איך
    -1.46
    zzly
    -1.43
     taky
    -1.42
    POSITIVE LOGITS
     that
    2.27
     they
    2.03
     такого
    1.68
     this
    1.68
     of
    1.54
     этого
    1.52
     ★★★★
    1.51
     after
    1.41
     його
    1.40
     then
    1.39
    Activations Density 0.069%

    No Known Activations