© 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. 9388
    Prev
    Next
    INDEX
    Explanations

    pursue a career or goal

    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
     {
    -2.94
    </
    -2.66
     The
    -2.66
     It
    -2.63
     they
    -2.56
     we
    -2.52
     you
    -2.44
    </h1>
    -2.44
     pomysł
    -2.41
    },
    -2.36
    POSITIVE LOGITS
     土産
    2.63
     They
    2.39
     estante
    2.36
    Николай
    2.33
    焌
    2.23
    ⛦
    2.19
    钌
    2.16
     排骨
    2.14
    это
    2.09
    更何况
    2.08
    Activations Density 0.003%

    No Known Activations