© 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. 22-GEMMASCOPE-RES-131K
    7. 73216
    Prev
    Next
    INDEX
    Explanations

    sentence endings

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

    The neuron fires on factual, instructional passages describing game mechanics or quantitative details—especially in‐game currency, items, and related stats.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ohne
    -1.26
     our
    -1.23
    οντας
    -1.18
     kollu
    -1.12
    ложений
    -1.12
    ⅘
    -1.11
    fehler
    -1.11
    ଂ
    -1.07
    getClassLoader
    -1.02
    ⅜
    -1.02
    POSITIVE LOGITS
     you
    2.11
     each
    1.66
     there
    1.58
     can
    1.48
     also
    1.45
    There
    1.43
     when
    1.37
    You
    1.35
     Each
    1.33
     they
    1.29
    Activations Density 0.029%

    No Known Activations