© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5998
    Prev
    Next
    INDEX
    Explanations

    play choices: Rock, Paper, Scissors

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

    The neuron flags numeric tokens, i.e. standalone numbers (often measurements or counts) in the text.

    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_24_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
     اړه
    0.72
     వివిధ
    0.63
    éticas
    0.59
    ppling
    0.58
     회
    0.57
    ρική
    0.57
    istet
    0.56
    埶
    0.56
    一系列
    0.55
    engaruhi
    0.55
    POSITIVE LOGITS
     because
    0.86
     thousand
    0.85
     porque
    0.80
     oppure
    0.79
    ’.
    0.78
    ”.
    0.77
    '.
    0.77
     hundred
    0.76
    !!!
    0.75
     quando
    0.75
    Activations Density 0.796%

    No Known Activations