© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10997
    Prev
    Next
    INDEX
    Explanations

    go-

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

    This neuron detects occurrences of the substring “go” (in any casing or as part of larger tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    उ
    0.62
    ᱚ
    0.55
     recuerdo
    0.55
    ève
    0.54
     분명
    0.54
    gable
    0.54
    捭
    0.53
    脸
    0.52
     hablando
    0.52
    臉
    0.52
    POSITIVE LOGITS
     forth
    0.67
    forward
    0.62
     forward
    0.60
    forth
    0.60
     вперед
    0.59
     downstream
    0.56
     Fenton
    0.56
    稠
    0.55
     north
    0.52
    grained
    0.52
    Activations Density 0.050%

    No Known Activations