© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6611
    Prev
    Next
    INDEX
    Explanations

    The neuron detects words that describe scenic viewpoints or views (e.g. overlooking, views, coast, sea, etc.).

    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
     humano
    0.75
    산업
    0.75
     incompat
    0.72
     IGBT
    0.69
     대응
    0.68
    PROTON
    0.67
     প্রতিরোধ
    0.66
    ()!=
    0.66
     autonom
    0.65
     DBMS
    0.65
    POSITIVE LOGITS
    景色
    1.36
     sunsets
    1.30
     panoramic
    1.22
     views
    1.19
     scenery
    1.15
     sunset
    1.13
    sunset
    1.08
     paisajes
    1.06
     vistas
    1.05
     unobstructed
    1.04
    Activations Density 0.360%

    No Known Activations