© 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. 77914
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and questions

    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
     Mural
    -0.82
     spite
    -0.81
     Lek
    -0.77
     rely
    -0.75
    ÓD
    -0.74
     Rely
    -0.73
     στον
    -0.73
     tháng
    -0.73
     Fet
    -0.73
     relying
    -0.72
    POSITIVE LOGITS
    8
    0.82
    
    0.79
    5
    0.77
    analytical
    0.76
     Hl
    0.76
     radix
    0.73
    స్తు
    0.70
    FileVersion
    0.70
     amplitudes
    0.69
    stdio
    0.68
    Activations Density 0.106%

    No Known Activations