© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130374
    Prev
    Next
    INDEX
    Explanations

    functions, factor, coherence, spectrum

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

    The neuron fires strongly on technical quantitative terms in scientific abstracts—especially occurrences of words like “functions,” “factor(s),” “transmission,” “coherence,” etc., i.e. names of mathematical or physical measures.

    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
     zamiast
    -1.48
    eapples
    -1.48
     financiera
    -1.45
    eapple
    -1.41
     partecipanti
    -1.40
    cadilly
    -1.40
     but
    -1.40
     direitos
    -1.38
     toallas
    -1.37
    ricing
    -1.36
    POSITIVE LOGITS
    Ƭ
    1.35
    のです
    1.34
     perpé
    1.32
     น
    1.27
     elucidate
    1.27
    './
    1.24
     reproduced
    1.24
     on
    1.23
     futura
    1.23
    borderSide
    1.20
    Activations Density 0.050%

    No Known Activations