© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70678
    Prev
    Next
    INDEX
    Explanations

    specific noun phrases or descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on proper names and other named‐entity tokens (people, places, organizations, wars, and dates).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     včetně
    -1.27
    翆
    -1.25
     TOPOLOGY
    -1.23
     daß
    -1.18
     psz
    -1.13
     🥰
    -1.11
    ᾿
    -1.11
    Ỷ
    -1.09
     ـ
    -1.09
     hispan
    -1.09
    POSITIVE LOGITS
     they
    1.50
     because
    1.36
    </tr>
    1.27
     äußer
    1.26
     their
    1.22
    Ketika
    1.17
    sepatu
    1.16
    subsection
    1.15
     vorigen
    1.13
     wouldn
    1.13
    Activations Density 0.046%

    No Known Activations