© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14676
    Prev
    Next
    INDEX
    Explanations

    world topics

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

    This neuron strongly activates on the final content token of each text segment, i.e. it marks the last word before a segment end.

    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
    !,
    0.69
    ;
    0.66
    !;
    0.64
    !:
    0.61
    ,
    0.60
    !”,
    0.58
    !),
    0.57
    ®,
    0.53
    !...
    0.53
    !);
    0.52
    POSITIVE LOGITS
     copyspace
    0.58
     reembolso
    0.50
     pozycji
    0.50
     pegar
    0.49
    があった
    0.47
     supprimer
    0.47
     pertenec
    0.46
     তাছাড়া
    0.46
    decoded
    0.46
    cego
    0.46
    Activations Density 0.001%

    No Known Activations