© 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. 79833
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     some
    -1.30
     to
    -1.25
     lastly
    -1.16
     until
    -1.16
     finally
    -1.14
    zeć
    -1.11
     />
    -1.09
    などを
    -1.08
    Adapun
    -1.08
    <bos>
    -1.05
    POSITIVE LOGITS
     estekak
    1.30
                                   
    1.12
    Mr
    1.05
     plastiques
    1.04
    iramente
    1.04
    を見ながら
    1.03
    毫无
    1.02
    xus
    1.02
    Sep
    1.02
                                  
    1.02
    Activations Density 0.007%

    No Known Activations