© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 205
    Prev
    Next
    INDEX
    Explanations

    acting against or targeting

    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
     was
    -2.81
    ”
    -2.53
    *
    -2.53
      
    -2.44
    </h2>
    -2.44
     is
    -2.14
    ]
    -2.14
    遑
    -2.08
     S
    -2.06
        
    -2.03
    POSITIVE LOGITS
     dezelve
    2.83
    CHREIB
    2.78
     estadounid
    2.53
    ﮯ
    2.47
    Uwaga
    2.45
     zoude
    2.44
    zestaw
    2.42
    
    2.42
    Warto
    2.42
     hunne
    2.41
    Activations Density 0.021%

    No Known Activations