© 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. 10866
    Prev
    Next
    INDEX
    Explanations

    the effect of

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

    The neuron responds to numeric substrings (page or image index numbers) embedded in the scanned‐page file names.

    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
     utford
    -1.09
     nivå
    -1.09
    tapete
    -1.08
     verlo
    -1.08
    boite
    -1.07
    hitung
    -1.06
     réinitial
    -1.06
    jadwal
    -1.06
     beleid
    -1.05
    cuc
    -1.04
    POSITIVE LOGITS
     et
    1.16
    ys
    1.13
    es
    1.11
    N
    1.04
    tel
    1.03
    </em>
    1.02
    mel
    1.02
    k
    1.01
    ha
    0.98
    les
    0.98
    Activations Density 0.001%

    No Known Activations