© 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. 8177
    Prev
    Next
    INDEX
    Explanations

    fil, Cull, pronunciation, today

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

    The neuron isn’t really looking for any particular word or meaning – it simply spikes on whatever token happens to fall in roughly the same slot (middle) of each input chunk.

    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
    ты
    0.84
    тные
    0.79
    iduciary
    0.79
    довой
    0.77
    во
    0.77
     Только
    0.77
    ნენ
    0.77
     encarg
    0.76
    riy
    0.75
    ாளர்கள்
    0.75
    POSITIVE LOGITS
    Pada
    0.83
    Ứ
    0.81
    Nella
    0.77
     ای
    0.76
     ANALYSIS
    0.75
     حکمت
    0.75
     LOCATION
    0.74
    MUX
    0.74
    KER
    0.73
    Imagenes
    0.72
    Activations Density 0.000%

    No Known Activations