© 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. 69047
    Prev
    Next
    INDEX
    Explanations

    Api constructor

    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
    
    -1.69
     kazak
    -1.69
     inaugura
    -1.68
     parlement
    -1.67
     hırka
    -1.64
     senin
    -1.62
     anadolu
    -1.60
    擽
    -1.60
     effici
    -1.59
     hant
    -1.59
    POSITIVE LOGITS
     ”
    1.75
     It
    1.67
     ''
    1.51
    --
    1.51
     for
    1.45
     if
    1.45
     can
    1.44
    !
    1.38
     h
    1.38
     on
    1.37
    Activations Density 1.735%

    No Known Activations