© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84255
    Prev
    Next
    INDEX
    Explanations

    simple, works, fine, smooth, straightforward

    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
     will
    -1.17
     atlik
    -0.98
    mitos
    -0.94
     in
    -0.94
     instead
    -0.93
     including
    -0.93
     from
    -0.93
    !
    -0.92
     includes
    -0.90
     may
    -0.88
    POSITIVE LOGITS
     แต่
    1.21
    generally
    1.17
    However
    1.17
    のですが
    1.10
    usual
    1.09
    But
    1.09
    usually
    1.08
    だったが
    1.04
    わけです
    1.04
    Then
    1.04
    Activations Density 0.434%

    No Known Activations