© 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. 10-GEMMASCOPE-RES-131K
    7. 104919
    Prev
    Next
    INDEX
    Explanations

    of the

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

    The neuron fires on list‐style count phrases—specifically the “some of [number]” constructions that introduce a numbered list or set of examples.

    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
    on
    -1.82
    to
    -1.77
    we
    -1.66
    us
    -1.52
    whether
    -1.51
     I
    -1.49
    our
    -1.47
    me
    -1.45
    ..........
    -1.44
     a
    -1.40
    POSITIVE LOGITS
     the
    1.73
    impinan
    1.58
    ︒
    1.52
     reacciones
    1.51
     also
    1.49
     how
    1.45
    嫚
    1.45
     ہیں۔
    1.44
     just
    1.43
    ăți
    1.42
    Activations Density 0.018%

    No Known Activations