© 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. 3135
    Prev
    Next
    INDEX
    Explanations

    I am designed to

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

    The neuron chiefly identifies direct second-person address—instances of “you” (and related reader-addressing constructions).

    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
     July
    1.11
     two
    1.10
     February
    1.09
     September
    1.09
     June
    1.07
     K
    1.06
     four
    1.06
     January
    1.05
     six
    1.02
     B
    1.02
    POSITIVE LOGITS
    utilizzo
    1.28
    ที่จะ
    1.22
    しっかりと
    1.14
    สิ่งที่
    1.14
    能够
    1.12
    を用いて
    1.11
    Allows
    1.10
    ことができる
    1.06
     посредством
    1.06
     umiejęt
    1.06
    Activations Density 4.584%

    No Known Activations