© 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. 10845
    Prev
    Next
    INDEX
    Explanations

    haiku, halifax, halley, harmonize

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

    The neuron spikes whenever it sees a token beginning with the letters “ha” (e.g. Haiku, Haj…, Habring, hair…).

    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
    chinen
    0.58
    軫
    0.57
     स्वरूप
    0.54
    샅
    0.54
    ாத
    0.53
     Promises
    0.52
    컸
    0.52
    یش
    0.52
    StoreID
    0.52
    逦
    0.50
    POSITIVE LOGITS
     HAB
    0.68
    Ha
    0.67
    ulte
    0.66
     ഹാ
    0.66
     HAV
    0.66
    bitat
    0.65
     Ha
    0.64
     Haver
    0.64
    郝
    0.64
     Hav
    0.63
    Activations Density 0.284%

    No Known Activations