© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9568
    Prev
    Next
    INDEX
    Explanations

    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_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
     znam
    -0.85
    五三
    -0.81
    wf
    -0.81
     žena
    -0.79
     podla
    -0.78
     sklo
    -0.78
    和田
    -0.77
     slova
    -0.77
     farmed
    -0.75
     tarto
    -0.75
    POSITIVE LOGITS
     or
    1.27
     Alternatively
    1.27
     instead
    1.27
    Alternatively
    1.20
    Instead
    1.16
     zamiast
    1.14
    instead
    1.13
     alternatively
    1.10
    代替
    1.06
     вместо
    1.05
    Activations Density 0.014%

    No Known Activations