© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27353
    Prev
    Next
    INDEX
    Explanations

    location or position

    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
     to
    -1.25
     from
    -1.15
     and
    -1.08
     in
    -0.94
     especially
    -0.93
    ológicos
    -0.92
     propias
    -0.88
     which
    -0.88
     nuevamente
    -0.87
     particularly
    -0.85
    POSITIVE LOGITS
     fonde
    1.05
    プション
    1.01
     annon
    0.97
     apport
    0.92
     fera
    0.91
     brille
    0.91
     oubli
    0.90
     rê
    0.90
     paillettes
    0.90
     interag
    0.89
    Activations Density 0.066%

    No Known Activations