© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9711
    Prev
    Next
    INDEX
    Explanations

    but or typically

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

    The neuron activates on language referring to altruistic or charitable activities (e.g. volunteer work, good works, purpose).

    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
     initio
    0.63
     resultant
    0.62
     microprocessor
    0.57
     perjury
    0.57
     heresy
    0.56
    虽
    0.55
    雖
    0.54
     indeterminate
    0.54
    ኅ
    0.54
     unmodified
    0.53
    POSITIVE LOGITS
     عشان
    0.83
     ولكن
    0.82
     लेकिन
    0.80
     bisschen
    0.80
     있는데
    0.80
     కూడా
    0.78
    พูด
    0.77
     things
    0.77
     También
    0.77
     이렇게
    0.77
    Activations Density 0.042%

    No Known Activations