© 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. 22-GEMMASCOPE-RES-131K
    7. 71154
    Prev
    Next
    INDEX
    Explanations

    occurrence of two

    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_22/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
    ꪀ
    -0.94
     all
    -0.90
     všetko
    -0.88
     trio
    -0.87
     følgende
    -0.87
    mates
    -0.85
     other
    -0.84
     third
    -0.84
     various
    -0.84
     Stellung
    -0.83
    POSITIVE LOGITS
    两种
    1.38
     दो
    1.18
     δύο
    1.13
    兩種
    1.09
    separate
    1.07
     halve
    1.05
    両方
    1.05
     ambas
    1.02
    Twice
    1.02
     TWO
    1.01
    Activations Density 0.158%

    No Known Activations