© 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. 80707
    Prev
    Next
    INDEX
    Explanations

    comic book titles and creators

    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
     cockpit
    -0.74
    Constantes
    -0.73
     Newtonsoft
    -0.71
    谈
    -0.71
    lně
    -0.71
    amoja
    -0.70
    стьян
    -0.70
     sunt
    -0.70
    networking
    -0.68
     piment
    -0.68
    POSITIVE LOGITS
    gau
    0.79
    minin
    0.71
    grass
    0.69
    κης
    0.68
    vor
    0.68
     WOR
    0.68
     을
    0.68
     song
    0.67
     Rough
    0.67
    ֠
    0.66
    Activations Density 0.047%

    No Known Activations