© 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. 12264
    Prev
    Next
    INDEX
    Explanations

    code, data, and separators

    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
     estadía
    -1.11
    ließen
    -0.99
     এবং
    -0.94
    ЕРИ
    -0.93
    гот
    -0.93
    tiques
    -0.91
    数料
    -0.91
     cárcel
    -0.90
    펭
    -0.90
    bourhood
    -0.89
    POSITIVE LOGITS
     all
    1.02
     From
    0.93
     distinctly
    0.92
     subtly
    0.91
    赞
    0.87
     separate
    0.85
    —
    0.85
     Taking
    0.84
    キ
    0.83
    べ
    0.83
    Activations Density 0.011%

    No Known Activations