© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5439
    Prev
    Next
    INDEX
    Explanations

    available

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

    The neuron fires on words and phrases indicating that something is available or accessible (e.g., “available,” “availability,” “accessible”).

    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
     TreeNode
    0.71
     breakaway
    0.64
    万人
    0.64
    fear
    0.62
    剩下的
    0.62
    ことになる
    0.61
     parvenir
    0.59
    ("/{
    0.59
    นิยม
    0.57
     kuris
    0.57
    POSITIVE LOGITS
    AVAILABLE
    0.92
     dostęp
    0.90
     gratuitamente
    0.87
     disponíveis
    0.85
     disponível
    0.82
    available
    0.80
    Available
    0.80
     دسترس
    0.79
    ogast
    0.77
     available
    0.75
    Activations Density 0.195%

    No Known Activations