© 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. 3014
    Prev
    Next
    INDEX
    Explanations

    offered courses and classes

    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
     acompañar
    -0.89
    åd
    -0.85
    gradation
    -0.84
     altavoz
    -0.83
    eli
    -0.83
     procesador
    -0.82
    send
    -0.82
     comien
    -0.81
    pyrid
    -0.81
    Ỳ
    -0.81
    POSITIVE LOGITS
     conducted
    1.97
     taught
    1.85
     offered
    1.84
    offered
    1.57
     held
    1.50
    taught
    1.50
     Offered
    1.44
    conducted
    1.44
    Offered
    1.35
     Taught
    1.22
    Activations Density 0.042%

    No Known Activations