© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40177
    Prev
    Next
    INDEX
    Explanations

    piercing pagoda

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

    The neuron fires on lines beginning with a “*” (asterisk) bullet or decorative star marker, as used in comment blocks and list formatting.

    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
     then
    -1.88
     augen
    -1.49
    、
    -1.47
     działalności
    -1.38
     additionally
    -1.31
     zrobić
    -1.27
     Bíblia
    -1.26
    lindung
    -1.24
    他说
    -1.24
    t
    -1.23
    POSITIVE LOGITS
     and
    1.81
     we
    1.60
     estómago
    1.44
     essas
    1.44
    these
    1.40
    those
    1.38
    咈
    1.32
    your
    1.29
    原始内容
    1.27
    AZIONI
    1.27
    Activations Density 0.000%

    No Known Activations