© 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. 89863
    Prev
    Next
    INDEX
    Explanations

    stop, stay, spoke, lose

    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
     весьма
    -1.24
    !
    -1.23
     awesome
    -1.09
     далее
    -1.07
     very
    -1.05
     via
    -1.01
     +
    -0.98
     totally
    -0.97
    也非常
    -0.96
    ).
    -0.95
    POSITIVE LOGITS
    hafte
    1.20
    ………………
    1.18
     .............
    1.16
     ............
    1.14
    hline
    1.14
     ...........
    1.12
    ится
    1.12
     chofe
    1.11
    なんて
    1.11
    toxicity
    1.10
    Activations Density 0.048%

    No Known Activations