© 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. 79651
    Prev
    Next
    INDEX
    Explanations

    the following

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

    The neuron fires on words that explicitly point to or specify particular things—e.g. definite articles (“the”), demonstratives (“these”), and precision-implying adjectives (“exact,” “perfect”).

    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
    กลุ่ม
    -1.13
     impecable
    -1.05
    truction
    -1.05
     of
    -1.05
    選擇
    -1.01
    🦔
    -0.99
    _{+}
    -0.98
    つまり
    -0.97
    mamp
    -0.97
     qualité
    -0.97
    POSITIVE LOGITS
     necessary
    2.09
     needed
    2.00
     a
    1.87
    needed
    1.68
     required
    1.65
     requisite
    1.65
     desired
    1.52
    dding
    1.49
     appropriate
    1.45
    necessary
    1.41
    Activations Density 0.094%

    No Known Activations