© 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. 10-GEMMASCOPE-RES-131K
    7. 90740
    Prev
    Next
    INDEX
    Explanations

    success or luck followed by action

    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_10/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
     a
    -1.98
     an
    -1.56
     for
    -1.56
     how
    -1.55
     need
    -1.54
     sikkert
    -1.51
     what
    -1.48
    泺
    -1.45
    徧
    -1.45
     if
    -1.45
    POSITIVE LOGITS
     with
    1.89
    </b>
    1.64
     }^{*}
    1.52
     meh
    1.48
     других
    1.42
     keduanya
    1.41
     mereka
    1.37
     Storing
    1.37
     GETTING
    1.37
    Again
    1.35
    Activations Density 0.041%

    No Known Activations