© 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. 12181
    Prev
    Next
    INDEX
    Explanations

    numeric sequences and citations

    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
    »),
    -1.02
    trash
    -0.96
    typen
    -0.96
    …
    -0.94
    ynka
    -0.94
    рю
    -0.94
    everyone
    -0.92
     gitara
    -0.91
    odziel
    -0.91
    മാ
    -0.91
    POSITIVE LOGITS
     бого
    0.86
     Pandemie
    0.85
     governador
    0.83
    }:\
    0.82
    용
    0.82
    ğlık
    0.81
     several
    0.80
     many
    0.79
     algal
    0.79
     دریافت‌شده
    0.79
    Activations Density 0.000%

    No Known Activations