© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65227
    Prev
    Next
    INDEX
    Explanations

    comparative phrases, questions, or lists

    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
    로드
    -1.05
     my
    -1.02
    ATUM
    -1.02
    ｗｗｗ
    -0.98
    ９
    -0.96
     other
    -0.93
    ！』
    -0.93
    erobic
    -0.92
     like
    -0.90
    而出
    -0.90
    POSITIVE LOGITS
     seçenek
    1.20
    塀
    1.20
     imidlertid
    1.19
     siguientes
    1.17
     ejemplos
    1.16
     exemplos
    1.16
    惋
    1.14
    choix
    1.13
    obrá
    1.12
     aktualisiert
    1.11
    Activations Density 0.000%

    No Known Activations