© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66333
    Prev
    Next
    INDEX
    Explanations

    by Category

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

    The neuron detects section headers or link teasers that introduce related or recommended content (e.g. “More…,” “Most…,” “You May Also Like,” etc.).

    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
    ur
    -1.38
     also
    -1.38
     chocolat
    -1.20
    ilu
    -1.18
    achu
    -1.15
     gebru
    -1.15
    лем
    -1.13
     également
    -1.13
    or
    -1.13
    hen
    -1.11
    POSITIVE LOGITS
     such
    1.82
     poszczegól
    1.51
     different
    1.41
    很棒
    1.38
     nuevas
    1.38
     этой
    1.33
     Algunos
    1.32
    PvB
    1.32
    település
    1.32
    including
    1.31
    Activations Density 0.020%

    No Known Activations