© 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. 11493
    Prev
    Next
    INDEX
    Explanations

    specific entities and abbreviations

    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
    tku
    -1.61
     digunakan
    -1.60
     gasolina
    -1.57
    zji
    -1.55
     jú
    -1.55
    مقدمه
    -1.53
     sonda
    -1.53
    桄
    -1.52
     lás
    -1.50
     kompeti
    -1.50
    POSITIVE LOGITS
    I
    1.66
    '
    1.61
    d
    1.59
    L
    1.56
    T
    1.53
    N
    1.53
    E
    1.53
    ar
    1.52
    u
    1.46
    j
    1.45
    Activations Density 0.013%

    No Known Activations