© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1253
    Prev
    Next
    INDEX
    Explanations

    point in time or condition

    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
    Areas
    -0.90
    areas
    -0.89
     microfibra
    -0.89
    environments
    -0.85
    写真は
    -0.85
    ifiques
    -0.85
     背包
    -0.85
    욘
    -0.85
    answered
    -0.85
     Traité
    -0.84
    POSITIVE LOGITS
     expense
    1.56
     juncture
    1.53
     glance
    1.45
     level
    1.38
     outset
    1.31
     location
    1.30
     intervals
    1.28
     discretion
    1.28
     pace
    1.20
     Glance
    1.20
    Activations Density 0.124%

    No Known Activations