© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65365
    Prev
    Next
    INDEX
    Explanations

    release date

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

    The neuron selectively activates on multi‐digit numeric tokens (i.e. numbers with two or more digits).

    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
    Εκ
    -1.38
    Παρα
    -1.26
    Δια
    -1.20
    Και
    -1.18
    Για
    -1.18
    Πα
    -1.18
     funkci
    -1.15
    rófono
    -1.15
     Meksi
    -1.14
    Dokument
    -1.13
    POSITIVE LOGITS
    e
    1.37
    d
    1.34
    a
    1.34
    y
    1.32
    f
    1.30
    t
    1.28
    T
    1.25
    l
    1.24
    i
    1.20
    in
    1.18
    Activations Density 0.039%

    No Known Activations