© 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. 34-GEMMASCOPE-RES-131K
    7. 83988
    Prev
    Next
    INDEX
    Explanations

    big deal

    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_34/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
     Entste
    -0.73
     tamén
    -0.73
     oamen
    -0.72
    uguetes
    -0.71
    ndares
    -0.70
    abro
    -0.68
    做得
    -0.68
    }}"
    -0.68
     firs
    -0.67
    modulo
    -0.67
    POSITIVE LOGITS
     deal
    5.81
    deal
    4.19
     Deal
    4.06
    Deal
    3.89
     DEAL
    3.47
     deals
    3.22
    DEAL
    2.86
     dealt
    2.77
     dealing
    2.48
     Deals
    2.45
    Activations Density 0.026%

    No Known Activations