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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8571
    Prev
    Next
    INDEX
    Explanations

    doing something or not

    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
     faciliter
    -1.28
    paravant
    -1.19
     garantir
    -1.16
     sirop
    -1.15
    美味し
    -1.15
     劇場
    -1.14
     accepter
    -1.13
    ఽ
    -1.12
     tikra
    -1.09
    herited
    -1.07
    POSITIVE LOGITS
     or
    2.84
     something
    1.89
     because
    1.43
     it
    1.41
     what
    1.41
     Usually
    1.41
     maybe
    1.38
     things
    1.35
     usually
    1.35
     doing
    1.32
    Activations Density 0.098%

    No Known Activations