© 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. 33055
    Prev
    Next
    INDEX
    Explanations

    problem and solution

    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
     AUSSI
    -1.05
     its
    -1.02
     unimportant
    -0.95
     улыба
    -0.94
     asust
    -0.91
    セラ
    -0.90
     outros
    -0.89
    EDEFAULT
    -0.88
    },[])
    -0.85
    
    -0.85
    POSITIVE LOGITS
     totiž
    1.41
     тогда
    1.20
     nämlich
    1.19
    特に
    1.16
    especially
    1.16
     simply
    1.11
    seem
    1.11
    seemed
    1.09
     bowiem
    1.09
     then
    1.09
    Activations Density 0.080%

    No Known Activations