© 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. 10911
    Prev
    Next
    INDEX
    Explanations

    items and activities

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

    The neuron is essentially a “thing” detector—it lights up on concrete countable noun tokens (objects or items).

    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
     to
    -1.13
     of
    -1.10
    Q
    -1.07
    Y
    -1.05
     möglicherweise
    -1.00
    v
    -1.00
    Some
    -1.00
    全体の
    -0.98
    His
    -0.97
     zusätzlich
    -0.97
    POSITIVE LOGITS
     decimos
    1.34
    rably
    1.30
    vább
    1.28
    roxene
    1.23
     karena
    1.18
    criminate
    1.13
    ecause
    1.13
    ਫ਼
    1.13
     komen
    1.12
    loed
    1.12
    Activations Density 0.047%

    No Known Activations