© 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. 34-GEMMASCOPE-RES-131K
    4. 110542
    Prev
    Next
    INDEX
    Explanations

    HTML code and text

    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
     by
    -1.20
     for
    -1.14
     Despite
    -1.12
     does
    -1.12
     However
    -1.05
     after
    -1.05
     to
    -1.05
     as
    -1.01
     so
    -1.00
     has
    -1.00
    POSITIVE LOGITS
    </
    1.38
     </
    1.20
     pivotal
    1.07
     níveis
    1.05
     réessayer
    1.03
    これも
    1.00
     extré
    0.99
    縢
    0.98
     dizendo
    0.98
    踯
    0.97
    Activations Density 0.011%

    No Known Activations