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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48446
    Prev
    Next
    INDEX
    Explanations

    extinct genus names

    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
     control
    -0.75
     Fl
    -0.70
     hot
    -0.68
    hamed
    -0.67
    をよく
    -0.67
     October
    -0.66
     biol
    -0.66
     silver
    -0.66
     match
    -0.66
     Jon
    -0.66
    POSITIVE LOGITS
    Terror
    0.93
    Illustration
    0.88
    Dunk
    0.87
     terror
    0.84
     géant
    0.84
    Zal
    0.82
     豊
    0.82
    手机
    0.81
     Terror
    0.81
     Penns
    0.79
    Activations Density 0.033%

    No Known Activations