© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2815
    Prev
    Next
    INDEX
    Explanations

    The neuron is selectively activated by decimal numbers (floating-point numerical values) in the text.

    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_31_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
    coff
    0.56
    mites
    0.51
    chec
    0.50
    ᐸ
    0.50
     এটিকে
    0.50
    capi
    0.49
    lable
    0.48
    ⁴
    0.48
    },(
    0.48
    ාව
    0.47
    POSITIVE LOGITS
     aad
    0.51
    凰
    0.48
     বাধ্য
    0.47
     অবশ্য
    0.45
    Your
    0.44
     Own
    0.44
     Your
    0.43
     refreshing
    0.43
    Anim
    0.42
     Kalian
    0.42
    Activations Density 0.145%

    No Known Activations