© 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. 13966
    Prev
    Next
    INDEX
    Explanations

    names like Blythe or Gamal

    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
     those
    -1.25
    ();
    -1.19
    AFFIRMED
    -1.18
    暨
    -1.17
     causation
    -1.16
     his
    -1.12
     suoi
    -1.11
     wyboru
    -1.08
     szczególnie
    -1.08
    ële
    -1.08
    POSITIVE LOGITS
    ですが
    1.19
    âteau
    1.11
     metode
    1.05
     toată
    1.04
     instead
    1.01
    内に
    0.99
    caya
    0.97
     Obwohl
    0.96
     Livre
    0.96
     apabila
    0.96
    Activations Density 0.189%

    No Known Activations