© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15527
    Prev
    Next
    INDEX
    Explanations

    end of sentence or explanation

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

    The neuron flags unusually rare or low‐frequency content words.

    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
    ﻕ
    0.91
    να
    0.88
     derivados
    0.85
     sebagian
    0.85
     inglesa
    0.85
     که
    0.83
     symmetric
    0.83
     যশোরের
    0.82
    鼈
    0.82
     некоторые
    0.82
    POSITIVE LOGITS
    idge
    1.03
    ди
    0.93
    icate
    0.81
    iddi
    0.79
    iche
    0.78
    i
    0.78
    chied
    0.77
    atine
    0.76
    idoo
    0.75
    ette
    0.74
    Activations Density 0.000%

    No Known Activations