© 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. 4296
    Prev
    Next
    INDEX
    Explanations

    published by

    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
     همه
    -0.90
    QueryBuilder
    -0.90
    tivas
    -0.84
    toor
    -0.82
    ⠀⠀⠀⠀
    -0.82
    ☼
    -0.82
    Qed
    -0.82
     Friends
    -0.81
    <0xED>
    -0.81
    Friends
    -0.80
    POSITIVE LOGITS
     drastic
    0.90
    了一些
    0.80
     because
    0.80
    Тек
    0.78
     noticeable
    0.77
    就可以了
    0.76
     taking
    0.75
     regardless
    0.75
     regret
    0.75
     only
    0.73
    Activations Density 0.007%

    No Known Activations