© 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. 10-GEMMASCOPE-RES-131K
    4. 104410
    Prev
    Next
    INDEX
    Explanations

    certificate

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

    the phrase "certificate of" in formal or official documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron flags mentions of official credentials or certification items (e.g. certificates, diplomas, completion units).

    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
    FFIX
    -1.59
    笵
    -1.57
     utilisé
    -1.48
    }
    -1.47
     ſen
    -1.45
     estos
    -1.44
     occuper
    -1.41
    阏
    -1.40
     différents
    -1.35
     muito
    -1.34
    POSITIVE LOGITS
    焄
    1.76
    on
    1.59
    Despite
    1.56
    With
    1.53
    Shortly
    1.49
    März
    1.45
    Without
    1.43
    Although
    1.42
    ★☆
    1.41
    嫗
    1.41
    Activations Density 0.032%

    No Known Activations