© 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. 75354
    Prev
    Next
    INDEX
    Explanations

    prepositions and locations

    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
     predecess
    -1.16
     controver
    -1.10
    設施
    -1.08
    鼱
    -1.08
     Republica
    -1.06
     intermit
    -1.03
    }],
    -1.02
     kilometer
    -1.00
     dégustation
    -1.00
     tef
    -0.98
    POSITIVE LOGITS
     both
    1.16
     in
    1.15
     this
    1.13
     your
    1.08
     fanns
    1.03
     these
    1.02
     very
    1.01
     our
    1.01
     نیز
    1.01
     great
    1.00
    Activations Density 0.052%

    No Known Activations