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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12352
    Prev
    Next
    INDEX
    Explanations

    before the first

    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
    良いです
    -1.05
    Finally
    -1.04
     Comentarios
    -1.02
     Popis
    -1.01
     Usar
    -1.00
    軽減
    -1.00
     lantaran
    -0.97
     Hvor
    -0.94
     Puoi
    -0.93
     Derfor
    -0.93
    POSITIVE LOGITS
     magasiner
    1.10
    はなく
    1.09
    を作り
    1.05
    zyć
    1.04
    ordat
    1.02
    ▶
    1.00
    ▎
    0.98
    には
    0.98
    局长
    0.98
     インチ
    0.96
    Activations Density 0.000%

    No Known Activations