© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33018
    Prev
    Next
    INDEX
    Explanations

    specific prefixes followed by specific tokens

    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
     úteis
    -1.38
     Características
    -1.38
     démission
    -1.32
     anunciado
    -1.30
    も多く
    -1.26
    ebly
    -1.24
     využ
    -1.24
     compétence
    -1.22
    ruka
    -1.16
    tető
    -1.16
    POSITIVE LOGITS
    <tfoot>
    1.44
           
    1.40
    </em>
    1.38
                      
    1.33
              
    1.31
             
    1.30
    1.29
                 
    1.24
       
    1.23
         
    1.22
    Activations Density 0.004%
    No Known Activations