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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11573
    Prev
    Next
    INDEX
    Explanations

    establishing, maintaining, improving, enabling

    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_22/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
     encargada
    -1.17
     to
    -1.16
     miteinander
    -1.12
     instead
    -1.11
     traditionellen
    -1.10
    bours
    -1.08
    だろうか
    -1.05
     ihren
    -1.05
    место
    -1.05
     странице
    -1.04
    POSITIVE LOGITS
     our
    1.79
     this
    1.74
     both
    1.61
     what
    1.55
     these
    1.52
     not
    1.43
     your
    1.38
     successfully
    1.32
     and
    1.31
     any
    1.26
    Activations Density 0.089%

    No Known Activations