© 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. 8552
    Prev
    Next
    INDEX
    Explanations

    names followed by numbers or context

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

    The neuron responds strongly to tokens that form place names (geographical location names).

    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
    -
    1.59
     नामक
    1.57
    ,
    1.54
    ’
    1.52
     adlı
    1.52
    .
    1.48
     and
    1.45
     மற்றும்
    1.45
     (
    1.36
    /
    1.35
    POSITIVE LOGITS
    UIntValue
    1.17
    pieceSelection
    1.15
     nontrivial
    1.15
    VerFile
    1.10
    ፈለ
    1.05
    timevals
    1.04
     childlike
    1.04
    elevationMap
    1.03
    parvec
    1.03
    ጠቀ
    1.03
    Activations Density 0.009%

    No Known Activations