© 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. 34-GEMMASCOPE-RES-131K
    7. 118944
    Prev
    Next
    INDEX
    Explanations

    cache and manifest

    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
    éfonos
    -0.81
    رائه
    -0.77
     prises
    -0.77
    ัจ
    -0.75
    canth
    -0.75
     FAV
    -0.75
     cote
    -0.74
     hablamos
    -0.73
    Precis
    -0.73
     incluida
    -0.73
    POSITIVE LOGITS
    CACHE
    0.90
    ผู้
    0.83
    Cache
    0.81
    พ
    0.77
     Kass
    0.77
     cach
    0.77
    Cash
    0.76
    __':
    0.76
     reasoned
    0.76
    út
    0.76
    Activations Density 0.022%

    No Known Activations