© 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. 34-GEMMASCOPE-RES-131K
    4. 2011
    Prev
    Next
    INDEX
    Explanations

    There,

    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_34/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
    \]
    
    -1.02
    ))->
    -0.92
    )="
    -0.88
    
    -0.87
     isto
    -0.84
    matical
    -0.83
    mmHg
    -0.83
    了些
    -0.81
    }));
    
    -0.80
    ⲓ
    -0.80
    POSITIVE LOGITS
    ,
    1.84
     they
    1.60
     you
    1.34
     we
    1.17
     it
    0.94
     geha
    0.92
    Where
    0.91
     тоже
    0.88
    Again
    0.86
    jących
    0.86
    Activations Density 0.021%

    No Known Activations