© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67658
    Prev
    Next
    INDEX
    Explanations

    start of text segments

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

    The neuron fires on occurrences of the token “begin,” i.e. markers that start sections or blocks.

    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
    but
    -3.00
    a
    -2.72
    and
    -2.67
     he
    -2.56
     “
    -2.48
     realizando
    -2.44
     zunächst
    -2.23
     then
    -2.22
     premiere
    -2.22
     mencion
    -2.20
    POSITIVE LOGITS
     ferrovia
    3.30
    鄚
    3.17
     \
    2.75
    咘
    2.73
     menyen
    2.69
    
    2.63
    メリカ
    2.61
    猡
    2.59
     合集
    2.56
     île
    2.55
    Activations Density 0.024%

    No Known Activations