© 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. 6757
    Prev
    Next
    INDEX
    Explanations

    working in specialized

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

    This neuron activates on floating‐point numbers (numeric tokens containing a decimal point with multiple digits).

    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
    len
    0.76
    c
    0.76
    })
    0.75
    l
    0.75
    ل
    0.74
    ler
    0.72
    els
    0.71
    }
    0.71
    ле
    0.69
    ede
    0.69
    POSITIVE LOGITS
    TAK
    0.91
     tatha
    0.91
     SDW
    0.90
     británico
    0.89
     ඇ
    0.88
     estadounid
    0.87
     Gestión
    0.86
     Дні
    0.86
     Phần
    0.85
    Sections
    0.84
    Activations Density 0.000%

    No Known Activations