© 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. 22-GEMMASCOPE-RES-131K
    7. 95742
    Prev
    Next
    INDEX
    Explanations

    among other things

    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
     túnel
    -1.11
    JAMIN
    -1.09
     炖
    -1.08
     tambah
    -1.05
    멜
    -1.04
    鱨
    -1.04
     and
    -1.03
    ᵗ
    -1.03
     aktiv
    -1.02
    ORDON
    -1.02
    POSITIVE LOGITS
    d
    1.31
     ailleurs
    1.26
    g
    1.23
    m
    1.23
     things
    1.22
     다른
    1.21
    s
    1.21
     other
    1.14
    is
    1.14
    w
    1.13
    Activations Density 0.015%

    No Known Activations