© 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. 12690
    Prev
    Next
    INDEX
    Explanations

    expected phrase

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

    This neuron is a position‐detector that fires strongly on the first few text chunks and then its activation decays over subsequent chunks, effectively marking how early in the document the current segment is.

    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
     목록
    0.81
     Пе
    0.80
    ى
    0.80
    renderCamera
    0.79
    엷
    0.76
    િ
    0.75
    𝓛
    0.75
     міся
    0.75
     Після
    0.75
    AudioAsset
    0.75
    POSITIVE LOGITS
    ado
    0.79
     via
    0.79
    }$-
    0.79
    s
    0.77
    '
    0.75
     Exc
    0.74
     cha
    0.73
     Gang
    0.73
     Glob
    0.73
    ndo
    0.72
    Activations Density 0.000%

    No Known Activations