© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 35013
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, links

    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
     Despite
    -1.15
     some
    -1.09
     that
    -1.07
    Despite
    -1.07
     However
    -1.01
     despite
    -1.00
     pushes
    -0.98
     just
    -0.97
     getting
    -0.97
     manchas
    -0.97
    POSITIVE LOGITS
     delightfully
    0.96
    ର
    0.94
     renowned
    0.89
     très
    0.88
     colossal
    0.88
     extravag
    0.86
     unfailing
    0.85
     boister
    0.85
    ╒
    0.84
     intrigu
    0.83
    Activations Density 0.153%

    No Known Activations