Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8685
    Prev
    Next
    INDEX
    Explanations

    to be verbs

    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
     is
    -1.34
     was
    -1.10
    äj
    -1.09
    が含ま
    -1.07
     ensured
    -1.06
     suele
    -1.05
     ensuring
    -1.05
    は
    -1.00
     aforementioned
    -0.97
     löytyy
    -0.96
    POSITIVE LOGITS
     be
    3.63
     være
    1.84
     להיות
    1.53
     être
    1.41
     essere
    1.40
     быть
    1.38
     being
    1.38
     być
    1.38
    être
    1.34
     باشد
    1.30
    Activations Density 0.057%

    No Known Activations