© 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. 19506
    Prev
    Next
    INDEX
    Explanations

    states of insecurity

    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
    但她
    -3.14
    The
    -2.72
    When
    -2.58
    In
    -2.45
     皇族
    -2.42
    ⇴
    -2.22
    ၞ
    -2.14
    縵
    -2.11
    remera
    -2.05
    緜
    -2.05
    POSITIVE LOGITS
     \
    2.33
    s
    2.19
     iets
    2.05
    所谓的
    1.88
    r
    1.88
    <bos>
    1.87
    Baylor
    1.84
     insecurity
    1.80
     koruyucu
    1.78
     insecurities
    1.77
    Activations Density 0.004%

    No Known Activations