© 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. 34-GEMMASCOPE-RES-131K
    7. 31250
    Prev
    Next
    INDEX
    Explanations

    a little, slightly

    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
    ]);
    -0.81
    =?,
    -0.80
     guidance
    -0.80
     APPLICABLE
    -0.79
    rindo
    -0.77
    
    -0.76
    нома
    -0.76
    別の
    -0.75
    сом
    -0.75
     SCHOL
    -0.74
    POSITIVE LOGITS
     slightly
    4.56
     немного
    4.34
     biraz
    4.22
    slightly
    3.98
    少し
    3.91
     abit
    3.86
     sedikit
    3.75
     trochę
    3.66
     etwas
    3.63
     Slightly
    3.58
    Activations Density 0.313%

    No Known Activations