© 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. 33875
    Prev
    Next
    INDEX
    Explanations

    clusters, modules, or areas

    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
     the
    -0.98
    resizingMask
    -0.95
    ∷
    -0.87
    titre
    -0.85
     duty
    -0.85
    equalTo
    -0.85
     to
    -0.85
    到位
    -0.84
    urd
    -0.84
    omato
    -0.84
    POSITIVE LOGITS
    ſter
    1.02
     smaller
    0.98
    私の
    0.94
     dAtA
    0.93
     groups
    0.93
    elsif
    0.92
    묶
    0.92
     identific
    0.92
    ର
    0.90
     formed
    0.90
    Activations Density 0.040%

    No Known Activations