© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87001
    Prev
    Next
    INDEX
    Explanations

    select item

    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
    “
    -2.06
     to
    -1.65
    ”
    -1.60
    still
    -1.48
     —
    -1.44
     mężczyzn
    -1.44
     and
    -1.43
    ти
    -1.41
    STILL
    -1.40
    “…
    -1.38
    POSITIVE LOGITS
    赑
    1.80
    <tr>
    1.66
     fallecido
    1.66
    総評
    1.63
    Banyak
    1.63
     cív
    1.55
    頃は
    1.55
    seamnă
    1.52
    鹛
    1.52
     ningún
    1.50
    Activations Density 0.014%

    No Known Activations