© 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. 10-GEMMASCOPE-RES-131K
    7. 85115
    Prev
    Next
    INDEX
    Explanations

    morally, Parents, corals, hurling

    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_10/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
    捽
    -2.56
    ſelves
    -2.48
    ization
    -2.33
    緇
    -2.33
    This
    -2.27
    ܜ
    -2.27
    These
    -2.25
    Many
    -2.16
    芣
    -2.14
     krav
    -2.11
    POSITIVE LOGITS
     Rückseite
    2.56
    of
    2.28
     ۶
    2.22
     небольшой
    2.17
     sogar
    2.14
    ,.
    2.06
    ↵↵
    2.03
     Menschheit
    2.02
     culmination
    2.02
     technischen
    2.02
    Activations Density 0.002%

    No Known Activations