© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32008
    Prev
    Next
    INDEX
    Explanations

    describing people or states

    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
     আম
    -1.03
    ße
    -0.93
    Anything
    -0.89
     outright
    -0.88
     hue
    -0.87
    banez
    -0.85
    が
    -0.81
     qualquer
    -0.79
    これを
    -0.79
    Le
    -0.78
    POSITIVE LOGITS
     because
    1.12
     femmin
    0.90
     resend
    0.87
    DeclareMath
    0.84
     bisschen
    0.84
    だと思います
    0.84
     therefor
    0.84
    袮
    0.81
    uerdo
    0.80
     officially
    0.80
    Activations Density 0.018%

    No Known Activations