© 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. 103489
    Prev
    Next
    INDEX
    Explanations

    describing a state or capability

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

    The neuron fires strongly on nouns that label formal attributes, roles, functions, or classifications (e.g. “status,” “function,” “role,” “duties,” “properties,” “activity,” “position”).

    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
    lloworld
    -1.13
     ASSOCIATES
    -1.13
     their
    -1.13
     måde
    -1.13
    nemers
    -1.10
    筥
    -1.09
     different
    -1.09
    遽
    -1.09
    blusa
    -1.08
     الجيش
    -1.08
    POSITIVE LOGITS
    6
    1.47
    such
    1.24
    —
    1.19
    3
    1.17
    </b>
    1.16
    мка
    1.13
    częściej
    1.13
     DON
    1.12
    pekte
    1.09
    4
    1.09
    Activations Density 0.104%

    No Known Activations