© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10166
    Prev
    Next
    INDEX
    Explanations

    platform

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

    This neuron fires strongly on the very first token of each new text segment, effectively marking segment or document boundaries.

    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
    𝙚
    0.88
    蜷
    0.83
    नून
    0.79
    ເນ
    0.77
    يو
    0.74
    சி
    0.72
    oxides
    0.72
    то
    0.71
    イギリス
    0.71
    தெ
    0.71
    POSITIVE LOGITS
    ?)
    0.83
     titulo
    0.79
     föret
    0.78
    });
    0.77
     tão
    0.77
    })$.
    0.76
     função
    0.75
    }).
    0.75
     či
    0.74
     telefone
    0.74
    Activations Density 0.001%

    No Known Activations