© 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. 57878
    Prev
    Next
    INDEX
    Explanations

    astronomical data and research papers

    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
     Oxford
    -0.73
    Facile
    -0.71
    Newport
    -0.69
     какая
    -0.69
    !!!!!!!!!!!!!!!!
    -0.67
     Evergreen
    -0.66
    VITA
    -0.66
     prostu
    -0.66
     Education
    -0.65
     Audible
    -0.65
    POSITIVE LOGITS
    Пу
    0.86
     reagieren
    0.85
    Související
    0.85
     ESO
    0.85
     coher
    0.84
    岗位
    0.84
    tagez
    0.84
    Saharan
    0.83
     disparo
    0.82
    ‚¬
    0.81
    Activations Density 0.025%

    No Known Activations