© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110870
    Prev
    Next
    INDEX
    Explanations

    except or but

    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
    :'',
    -0.96
    だけでも
    -0.94
    Ⅽ
    -0.87
    (''),
    -0.84
    
    -0.83
    vron
    -0.82
     MwSt
    -0.82
    ombang
    -0.82
     tikra
    -0.81
    uleb
    -0.80
    POSITIVE LOGITS
     except
    9.44
    except
    8.00
    Except
    7.06
     Except
    6.47
     EXCEPT
    5.59
     excepto
    5.38
    EXCEPT
    4.97
     sauf
    4.91
     exception
    4.72
     kecuali
    4.69
    Activations Density 0.788%

    No Known Activations