© 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. 34312
    Prev
    Next
    INDEX
    Explanations

    Outlook email user consequences

    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
    ついでに
    -1.02
     reassuring
    -1.02
    Informazioni
    -0.97
    いれば
    -0.94
     poissons
    -0.93
     écl
    -0.92
    得以
    -0.91
     vache
    -0.91
    海报
    -0.91
    Descriere
    -0.90
    POSITIVE LOGITS
     resulting
    1.16
    tonsoft
    1.13
     resulted
    1.08
     too
    1.06
     Estadual
    1.04
     khiến
    1.02
    맴
    1.00
    kový
    1.00
     Durchführung
    1.00
     without
    0.99
    Activations Density 0.072%

    No Known Activations