© 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. 1402
    Prev
    Next
    INDEX
    Explanations

    The neuron sharply activates on the word “Showers” (as in “Baby Showers”), i.e. it picks out that specific heading/token.

    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
    ﻟ
    0.93
    IANS
    0.89
    IIS
    0.89
     ulcerative
    0.82
    ILD
    0.80
    IAC
    0.78
    Chhattisgarh
    0.77
    INER
    0.77
    勍
    0.77
    FBSDKGraph
    0.77
    POSITIVE LOGITS
    ap
    0.85
     classique
    0.85
    us
    0.80
     преимуще
    0.77
    ain
    0.76
    ency
    0.76
     quid
    0.75
     boule
    0.73
     Name
    0.73
     fiel
    0.72
    Activations Density 0.000%

    No Known Activations