© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103664
    Prev
    Next
    INDEX
    Explanations

    URLs with path segments

    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
     Universidad
    -0.84
    okohama
    -0.83
    Francia
    -0.82
     }(
    -0.79
    loed
    -0.78
     funguje
    -0.78
    hicles
    -0.77
     deň
    -0.77
    ppins
    -0.77
     bọc
    -0.77
    POSITIVE LOGITS
    ∼
    1.43
    ˜
    1.34
     〜
    1.23
    ~
    1.19
     ∼
    1.18
    〜
    1.15
     ~
    1.14
    STAFF
    1.11
     people
    1.10
    people
    1.09
    Activations Density 0.037%

    No Known Activations