© 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. 91472
    Prev
    Next
    INDEX
    Explanations

    attracted research interest

    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
    álna
    -0.96
     some
    -0.90
    zonej
    -0.86
    zonego
    -0.86
    lète
    -0.85
     here
    -0.84
     at
    -0.84
     ї
    -0.84
     aquí
    -0.82
    地的
    -0.82
    POSITIVE LOGITS
     research
    2.34
     interest
    2.20
    Research
    1.70
    research
    1.67
    Interest
    1.63
     researching
    1.58
     Interest
    1.55
     researchers
    1.52
     pesquis
    1.49
    研究
    1.47
    Activations Density 0.474%

    No Known Activations