© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1285
    Prev
    Next
    INDEX
    Explanations

    free from negative conditions

    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
     chiare
    -0.98
     mettere
    -0.96
     piú
    -0.90
     particolari
    -0.88
     giusta
    -0.86
    があり
    -0.85
     buone
    -0.84
     ragioni
    -0.83
     citazioni
    -0.82
     caratteri
    -0.82
    POSITIVE LOGITS
     free
    3.63
    free
    3.09
    FREE
    2.47
     FREE
    2.36
     Free
    2.27
    Free
    2.27
     свобод
    1.90
    freie
    1.86
     беспла
    1.66
    無料
    1.61
    Activations Density 0.036%

    No Known Activations