© 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. 64947
    Prev
    Next
    INDEX
    Explanations

    expected or desired outcome/result

    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
     !!!!
    -1.20
    暑い
    -1.19
    Slf
    -1.16
    跸
    -1.16
    
    -1.15
     creación
    -1.14
    奁
    -1.09
     cinquième
    -1.09
    での
    -1.08
     ་
    -1.06
    POSITIVE LOGITS
     thinks
    1.12
    d
    1.08
    la
    1.07
    er
    1.06
     value
    1.05
    l
    1.03
    an
    1.02
     '>=
    1.01
    man
    1.00
    b
    1.00
    Activations Density 0.012%

    No Known Activations