© 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. 98856
    Prev
    Next
    INDEX
    Explanations

    Allah, Farah, hhhh sounds

    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
    ii
    -0.98
    ありません
    -0.89
    まして
    -0.78
     truly
    -0.78
    at
    -0.76
    imah
    -0.73
     garnish
    -0.73
    aban
    -0.72
    ello
    -0.71
    おめでとうございます
    -0.71
    POSITIVE LOGITS
    hhhh
    1.34
    hhh
    1.29
    hhhhhhhh
    1.26
    hhhhh
    1.20
    なくて
    1.05
    s
    1.03
    HHHH
    1.00
    slip
    1.00
    спери
    0.97
    hh
    0.96
    Activations Density 0.117%

    No Known Activations