© 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. 47679
    Prev
    Next
    INDEX
    Explanations

    2nd, 3rd, 5th

    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
     Cops
    -0.82
     realtor
    -0.80
    ющими
    -0.80
     pedi
    -0.78
     Tuning
    -0.75
     řed
    -0.73
     umí
    -0.73
     Varieties
    -0.73
    Bibitem
    -0.73
     焼
    -0.73
    POSITIVE LOGITS
    ''
    1.83
    '''
    1.69
     '''
    1.63
     ''
    1.61
     ``
    1.55
    .''
    1.49
    ‘’
    1.39
    ``
    1.36
    .’’
    1.33
    ‘‘
    1.30
    Activations Density 0.349%

    No Known Activations