© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 763
    Prev
    Next
    INDEX
    Explanations

    programming code keywords

    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_10/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
     összefoglal
    -1.73
    出して
    -1.70
    </h2>
    -1.66
     säga
    -1.64
    nitř
    -1.59
    excellents
    -1.52
     expédi
    -1.51
     kväll
    -1.49
     GOOD
    -1.48
     BOTH
    -1.48
    POSITIVE LOGITS
     we
    1.76
     is
    1.73
     were
    1.58
    簠
    1.41
     “
    1.41
    我们
    1.41
     seguintes
    1.37
    メルカリ
    1.37
     you
    1.34
     they
    1.34
    Activations Density 0.041%

    No Known Activations