© 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. 36366
    Prev
    Next
    INDEX
    Explanations

    service states and types

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

    The neuron fires most strongly on code identifiers (type/enum/class names and the like), i.e. CamelCase or all-caps tokens.

    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
     and
    -2.84
     or
    -1.54
     this
    -1.48
    為に
    -1.45
     brachten
    -1.42
     gedachten
    -1.41
     größe
    -1.38
     beberapa
    -1.28
     zeggen
    -1.27
    早晨
    -1.24
    POSITIVE LOGITS
    ignée
    1.48
    <bos>
    1.47
    着的
    1.45
    は
    1.44
     мебели
    1.43
    骉
    1.38
    arschijnlijk
    1.35
    檻
    1.34
    过去了
    1.34
    くれます
    1.34
    Activations Density 0.016%

    No Known Activations