© 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. 71510
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron is detecting four-digit numeric tokens that appear to be years (i.e. copyright or date-style numbers).

    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
     they
    -1.30
     its
    -1.30
    erobic
    -1.16
    yorum
    -1.16
    際の
    -1.08
     líqu
    -1.02
     institucional
    -1.02
     Amerikan
    -1.01
     educativa
    -0.98
    saucony
    -0.98
    POSITIVE LOGITS
    𝘦
    1.09
    e
    1.09
     државе
    1.07
    lambda
    1.06
    He
    1.06
    1.05
    ´
    1.05
    ins
    1.04
    ors
    1.02
    Ã
    1.02
    Activations Density 0.005%

    No Known Activations