© 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. 70257
    Prev
    Next
    INDEX
    Explanations

    obviously, clearly

    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
     şöyle
    -0.89
     пожа
    -0.87
    iterran
    -0.86
    也只是
    -0.84
    تيجة
    -0.84
     daarom
    -0.84
    pasta
    -0.81
     toujours
    -0.81
    шите
    -0.80
    θυ
    -0.79
    POSITIVE LOGITS
     obviously
    6.88
    obviously
    5.75
     Obviously
    5.47
    Obviously
    5.47
     clearly
    5.25
    显然
    5.00
    Clearly
    4.97
     Clearly
    4.94
     evidently
    4.63
    clearly
    4.31
    Activations Density 0.144%

    No Known Activations