© 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. 67967
    Prev
    Next
    INDEX
    Explanations

    according to

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

    The neuron is detecting sentence boundaries—particularly end‐of‐sentence punctuation (periods) and the start of the next sentence.

    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
    Cloudy
    -1.43
    邹
    -1.33
     绘画
    -1.33
    uniqlo
    -1.30
    whisky
    -1.26
    idać
    -1.25
     Misalnya
    -1.25
    playera
    -1.22
     Secara
    -1.21
     fierce
    -1.20
    POSITIVE LOGITS
    椟
    1.66
    ary
    1.65
     lakini
    1.59
    its
    1.55
    ent
    1.53
    快要
    1.47
    但
    1.45
     its
    1.45
    撂
    1.45
     tetapi
    1.44
    Activations Density 0.046%

    No Known Activations