© 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. 107186
    Prev
    Next
    INDEX
    Explanations

    field names in data or code

    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
     tématu
    -1.01
     adelant
    -0.96
     vervolgens
    -0.93
    Those
    -0.91
    licopter
    -0.90
     DATOS
    -0.85
    ترل
    -0.84
    sillon
    -0.82
    igts
    -0.81
     більш
    -0.81
    POSITIVE LOGITS
     date
    1.05
     value
    1.04
    เกม
    0.89
     ksi
    0.86
     sequence
    0.85
     golos
    0.84
     utilized
    0.84
    WithValue
    0.84
     fecha
    0.83
     VALUE
    0.83
    Activations Density 0.032%

    No Known Activations