© 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. 107908
    Prev
    Next
    INDEX
    Explanations

    setting formulas

    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
     cucchiai
    -1.13
    artamento
    -0.98
    álise
    -0.96
     подходит
    -0.93
    Prijs
    -0.90
    Aceite
    -0.89
    EOUT
    -0.85
     putem
    -0.85
    記入
    -0.84
    tagena
    -0.84
    POSITIVE LOGITS
     formula
    2.02
     formulas
    1.66
    formula
    1.59
     Formula
    1.50
     formulae
    1.38
     based
    1.36
     annually
    1.35
     calculation
    1.34
    Formula
    1.34
     FORMULA
    1.32
    Activations Density 0.017%

    No Known Activations