© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 69015
    Prev
    Next
    INDEX
    Explanations

    Czech Republic, UK sizing, backup, cancel, Agent, Street

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

    The neuron fires on structured-data tokens—uppercase labels, IDs, numeric values, and table-header or metadata terms.

    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
    </h2>
    -1.45
    ertia
    -1.43
    ကိုးက
    -1.30
    ಃ
    -1.27
    orul
    -1.27
     garant
    -1.26
     debo
    -1.25
     eventi
    -1.23
     débuts
    -1.23
     finner
    -1.22
    POSITIVE LOGITS
    ↵↵↵
    1.77
    ’
    1.41
     Following
    1.41
    ↵↵↵↵↵
    1.30
     ikiwa
    1.23
    _
    1.20
     commerciaux
    1.20
     eenige
    1.18
     років
    1.17
    ceuticals
    1.13
    Activations Density 0.333%

    No Known Activations