© 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. 34-GEMMASCOPE-RES-131K
    7. 91318
    Prev
    Next
    INDEX
    Explanations

    making evaluative statements

    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
     Reasons
    -0.88
     phenomena
    -0.87
     reasons
    -0.84
    舗
    -0.82
    reasons
    -0.78
    taxes
    -0.78
    Pozri
    -0.78
     fazendo
    -0.77
     Bereiche
    -0.77
     молодых
    -0.77
    POSITIVE LOGITS
     adjustments
    1.39
     decisions
    1.27
     mistake
    1.23
     headway
    1.22
    Decisions
    1.20
     discoveries
    1.15
     assumptions
    1.15
     assumption
    1.13
     strides
    1.13
     connections
    1.12
    Activations Density 0.047%

    No Known Activations