© 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. 107520
    Prev
    Next
    INDEX
    Explanations

    identifying correct answers

    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
    ваете
    -0.85
    simplex
    -0.74
    setTypeface
    -0.71
    dopodob
    -0.71
    ByEmail
    -0.71
    esteem
    -0.70
     смысл
    -0.69
    southwest
    -0.68
    énom
    -0.67
    强大的
    -0.67
    POSITIVE LOGITS
     correct
    7.25
    correct
    6.09
    Correct
    5.78
     Correct
    5.59
    正确
    4.81
     correctly
    4.69
     correctness
    4.69
     CORRECT
    4.66
    CORRECT
    4.44
     прави
    4.25
    Activations Density 0.233%

    No Known Activations