© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86268
    Prev
    Next
    INDEX
    Explanations

    multi-lingual text

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

    The neuron fires most strongly on concrete object or item nouns (e.g. names of tools, building types, firm names) appearing as examples in technical or list‐style contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    U
    -1.41
    w
    -1.41
    >
    -1.38
    ”
    -1.38
    f
    -1.31
    X
    -1.31
    和
    -1.30
    不需要
    -1.30
    他是
    -1.27
    j
    -1.26
    POSITIVE LOGITS
    慊
    1.55
     terão
    1.53
    Proveedor
    1.45
     навіть
    1.44
     poderão
    1.42
    豺
    1.42
    Ꮏ
    1.41
    clearing
    1.40
    ,\\
    1.39
    Organizador
    1.38
    Activations Density 0.379%

    No Known Activations