© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40000
    Prev
    Next
    INDEX
    Explanations

    despite the fact that

    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_22/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
     will
    -0.91
    bitrate
    -0.91
     сожалению
    -0.91
    dimension
    -0.88
     prêtre
    -0.87
     "¿
    -0.86
    schöne
    -0.84
     nationales
    -0.83
     Pena
    -0.83
     取付
    -0.83
    POSITIVE LOGITS
     pourtant
    1.83
     przecież
    1.35
     important
    1.21
     obvious
    1.18
     needed
    1.13
     crucial
    1.13
     vital
    1.03
     would
    1.02
     critical
    1.01
     supposed
    0.97
    Activations Density 0.075%

    No Known Activations