© 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. 15603
    Prev
    Next
    INDEX
    Explanations

    bonus tracks, extra content, remixes

    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
     our
    -1.79
     in
    -1.70
     at
    -1.41
     until
    -1.39
     or
    -1.37
     large
    -1.35
     without
    -1.30
     data
    -1.30
     Y
    -1.29
     when
    -1.29
    POSITIVE LOGITS
     développement
    1.69
     œufs
    1.52
     fabricant
    1.48
     diriger
    1.47
     favoriser
    1.44
     patate
    1.44
     corrom
    1.44
     perles
    1.43
     oeufs
    1.41
     renfer
    1.41
    Activations Density 0.013%

    No Known Activations